(dream) tb@IBM-PF38WZKF:~/funstreams/AI$ ./llama.cpp/quantize zephyr_f32.gguf Q3_K main: build = 1798 (128de35) main: built with cc (Ubuntu 9.4.0-1ubuntu1~20.04.2) 9.4.0 for x86_64-linux-gnu main: quantizing 'zephyr_f32.gguf' to 'ggml-model-Q3_K.gguf' as Q3_K llama_model_loader: loaded meta data with 22 key-value pairs and 291 tensors from zephyr_f32.gguf (version GGUF V3 (latest)) llama_model_loader: Dumping metadata keys/values. Note: KV overrides do not apply in this output. llama_model_loader: - kv 0: general.architecture str = llama llama_model_loader: - kv 1: general.name str = . llama_model_loader: - kv 2: llama.context_length u32 = 32768 llama_model_loader: - kv 3: llama.embedding_length u32 = 4096 llama_model_loader: - kv 4: llama.block_count u32 = 32 llama_model_loader: - kv 5: llama.feed_forward_length u32 = 14336 llama_model_loader: - kv 6: llama.rope.dimension_count u32 = 128 llama_model_loader: - kv 7: llama.attention.head_count u32 = 32 llama_model_loader: - kv 8: llama.attention.head_count_kv u32 = 8 llama_model_loader: - kv 9: llama.attention.layer_norm_rms_epsilon f32 = 0.000010 llama_model_loader: - kv 10: llama.rope.freq_base f32 = 10000.000000 llama_model_loader: - kv 11: general.file_type u32 = 0 llama_model_loader: - kv 12: tokenizer.ggml.model str = llama llama_model_loader: - kv 13: tokenizer.ggml.tokens arr[str,32000] = ["", "", "", "<0x00>", "<... llama_model_loader: - kv 14: tokenizer.ggml.scores arr[f32,32000] = [0.000000, 0.000000, 0.000000, 0.0000... llama_model_loader: - kv 15: tokenizer.ggml.token_type arr[i32,32000] = [2, 3, 3, 6, 6, 6, 6, 6, 6, 6, 6, 6, ... llama_model_loader: - kv 16: tokenizer.ggml.merges arr[str,58980] = ["▁ t", "i n", "e r", "▁ a", "h e... llama_model_loader: - kv 17: tokenizer.ggml.bos_token_id u32 = 1 llama_model_loader: - kv 18: tokenizer.ggml.eos_token_id u32 = 2 llama_model_loader: - kv 19: tokenizer.ggml.unknown_token_id u32 = 0 llama_model_loader: - kv 20: tokenizer.ggml.padding_token_id u32 = 2 llama_model_loader: - kv 21: tokenizer.chat_template str = {% for message in messages %}\n{% if m... llama_model_loader: - type f32: 291 tensors llama_model_quantize_internal: meta size = 1671648 bytes [ 1/ 291] token_embd.weight - [ 4096, 32000, 1, 1], type = f32, quantizing to q3_K .. size = 500.00 MiB -> 53.71 MiB | hist: [ 2/ 291] blk.0.attn_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MB [ 3/ 291] blk.0.ffn_down.weight - [14336, 4096, 1, 1], type = f32, quantizing to q5_K .. size = 224.00 MiB -> 38.50 MiB | hist: [ 4/ 291] blk.0.ffn_gate.weight - [ 4096, 14336, 1, 1], type = f32, quantizing to q3_K .. size = 224.00 MiB -> 24.06 MiB | hist: [ 5/ 291] blk.0.ffn_up.weight - [ 4096, 14336, 1, 1], type = f32, quantizing to q3_K .. size = 224.00 MiB -> 24.06 MiB | hist: [ 6/ 291] blk.0.ffn_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MB [ 7/ 291] blk.0.attn_k.weight - [ 4096, 1024, 1, 1], type = f32, quantizing to q3_K .. size = 16.00 MiB -> 1.72 MiB | hist: [ 8/ 291] blk.0.attn_output.weight - [ 4096, 4096, 1, 1], type = f32, quantizing to q4_K .. size = 64.00 MiB -> 9.00 MiB | hist: [ 9/ 291] blk.0.attn_q.weight - [ 4096, 4096, 1, 1], type = f32, quantizing to q3_K .. size = 64.00 MiB -> 6.88 MiB | hist: [ 10/ 291] blk.0.attn_v.weight - [ 4096, 1024, 1, 1], type = f32, quantizing to q5_K .. size = 16.00 MiB -> 2.75 MiB | hist: [ 11/ 291] blk.1.attn_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MB [ 12/ 291] blk.1.ffn_down.weight - [14336, 4096, 1, 1], type = f32, quantizing to q5_K .. size = 224.00 MiB -> 38.50 MiB | hist: [ 13/ 291] blk.1.ffn_gate.weight - [ 4096, 14336, 1, 1], type = f32, quantizing to q3_K .. size = 224.00 MiB -> 24.06 MiB | hist: [ 14/ 291] blk.1.ffn_up.weight - [ 4096, 14336, 1, 1], type = f32, quantizing to q3_K .. size = 224.00 MiB -> 24.06 MiB | hist: [ 15/ 291] blk.1.ffn_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MB [ 16/ 291] blk.1.attn_k.weight - [ 4096, 1024, 1, 1], type = f32, quantizing to q3_K .. size = 16.00 MiB -> 1.72 MiB | hist: [ 17/ 291] blk.1.attn_output.weight - [ 4096, 4096, 1, 1], type = f32, quantizing to q4_K .. size = 64.00 MiB -> 9.00 MiB | hist: [ 18/ 291] blk.1.attn_q.weight - [ 4096, 4096, 1, 1], type = f32, quantizing to q3_K .. size = 64.00 MiB -> 6.88 MiB | hist: [ 19/ 291] blk.1.attn_v.weight - [ 4096, 1024, 1, 1], type = f32, quantizing to q5_K .. size = 16.00 MiB -> 2.75 MiB | hist: [ 20/ 291] blk.2.attn_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MB [ 21/ 291] blk.2.ffn_down.weight - [14336, 4096, 1, 1], type = f32, quantizing to q4_K .. size = 224.00 MiB -> 31.50 MiB | hist: [ 22/ 291] blk.2.ffn_gate.weight - [ 4096, 14336, 1, 1], type = f32, quantizing to q3_K .. size = 224.00 MiB -> 24.06 MiB | hist: [ 23/ 291] blk.2.ffn_up.weight - [ 4096, 14336, 1, 1], type = f32, quantizing to q3_K .. size = 224.00 MiB -> 24.06 MiB | hist: [ 24/ 291] blk.2.ffn_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MB [ 25/ 291] blk.2.attn_k.weight - [ 4096, 1024, 1, 1], type = f32, quantizing to q3_K .. size = 16.00 MiB -> 1.72 MiB | hist: [ 26/ 291] blk.2.attn_output.weight - [ 4096, 4096, 1, 1], type = f32, quantizing to q4_K .. size = 64.00 MiB -> 9.00 MiB | hist: [ 27/ 291] blk.2.attn_q.weight - [ 4096, 4096, 1, 1], type = f32, quantizing to q3_K .. size = 64.00 MiB -> 6.88 MiB | hist: [ 28/ 291] blk.2.attn_v.weight - [ 4096, 1024, 1, 1], type = f32, quantizing to q4_K .. size = 16.00 MiB -> 2.25 MiB | hist: [ 29/ 291] blk.3.ffn_gate.weight - [ 4096, 14336, 1, 1], type = f32, quantizing to q3_K .. size = 224.00 MiB -> 24.06 MiB | hist: [ 30/ 291] blk.3.ffn_up.weight - [ 4096, 14336, 1, 1], type = f32, quantizing to q3_K .. size = 224.00 MiB -> 24.06 MiB | hist: [ 31/ 291] blk.3.attn_k.weight - [ 4096, 1024, 1, 1], type = f32, quantizing to q3_K .. size = 16.00 MiB -> 1.72 MiB | hist: [ 32/ 291] blk.3.attn_output.weight - [ 4096, 4096, 1, 1], type = f32, quantizing to q4_K .. size = 64.00 MiB -> 9.00 MiB | hist: [ 33/ 291] blk.3.attn_q.weight - [ 4096, 4096, 1, 1], type = f32, quantizing to q3_K .. size = 64.00 MiB -> 6.88 MiB | hist: [ 34/ 291] blk.3.attn_v.weight - [ 4096, 1024, 1, 1], type = f32, quantizing to q4_K .. size = 16.00 MiB -> 2.25 MiB | hist: [ 35/ 291] blk.3.attn_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MB [ 36/ 291] blk.3.ffn_down.weight - [14336, 4096, 1, 1], type = f32, quantizing to q4_K .. size = 224.00 MiB -> 31.50 MiB | hist: [ 37/ 291] blk.3.ffn_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MB [ 38/ 291] blk.4.attn_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MB [ 39/ 291] blk.4.ffn_down.weight - [14336, 4096, 1, 1], type = f32, quantizing to q4_K .. size = 224.00 MiB -> 31.50 MiB | hist: [ 40/ 291] blk.4.ffn_gate.weight - [ 4096, 14336, 1, 1], type = f32, quantizing to q3_K .. size = 224.00 MiB -> 24.06 MiB | hist: [ 41/ 291] blk.4.ffn_up.weight - [ 4096, 14336, 1, 1], type = f32, quantizing to q3_K .. size = 224.00 MiB -> 24.06 MiB | hist: [ 42/ 291] blk.4.ffn_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MB [ 43/ 291] blk.4.attn_k.weight - [ 4096, 1024, 1, 1], type = f32, quantizing to q3_K .. size = 16.00 MiB -> 1.72 MiB | hist: [ 44/ 291] blk.4.attn_output.weight - [ 4096, 4096, 1, 1], type = f32, quantizing to q4_K .. size = 64.00 MiB -> 9.00 MiB | hist: [ 45/ 291] blk.4.attn_q.weight - [ 4096, 4096, 1, 1], type = f32, quantizing to q3_K .. size = 64.00 MiB -> 6.88 MiB | hist: [ 46/ 291] blk.4.attn_v.weight - [ 4096, 1024, 1, 1], type = f32, quantizing to q4_K .. size = 16.00 MiB -> 2.25 MiB | hist: [ 47/ 291] blk.5.attn_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MB [ 48/ 291] blk.5.ffn_down.weight - [14336, 4096, 1, 1], type = f32, quantizing to q4_K .. size = 224.00 MiB -> 31.50 MiB | hist: [ 49/ 291] blk.5.ffn_gate.weight - [ 4096, 14336, 1, 1], type = f32, quantizing to q3_K .. size = 224.00 MiB -> 24.06 MiB | hist: [ 50/ 291] blk.5.ffn_up.weight - [ 4096, 14336, 1, 1], type = f32, quantizing to q3_K .. size = 224.00 MiB -> 24.06 MiB | hist: [ 51/ 291] blk.5.ffn_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MB [ 52/ 291] blk.5.attn_k.weight - [ 4096, 1024, 1, 1], type = f32, quantizing to q3_K .. size = 16.00 MiB -> 1.72 MiB | hist: [ 53/ 291] blk.5.attn_output.weight - [ 4096, 4096, 1, 1], type = f32, quantizing to q4_K .. size = 64.00 MiB -> 9.00 MiB | hist: [ 54/ 291] blk.5.attn_q.weight - [ 4096, 4096, 1, 1], type = f32, quantizing to q3_K .. size = 64.00 MiB -> 6.88 MiB | hist: [ 55/ 291] blk.5.attn_v.weight - [ 4096, 1024, 1, 1], type = f32, quantizing to q4_K .. size = 16.00 MiB -> 2.25 MiB | hist: [ 56/ 291] blk.6.attn_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MB [ 57/ 291] blk.6.ffn_down.weight - [14336, 4096, 1, 1], type = f32, quantizing to q4_K .. size = 224.00 MiB -> 31.50 MiB | hist: [ 58/ 291] blk.6.ffn_gate.weight - [ 4096, 14336, 1, 1], type = f32, quantizing to q3_K .. size = 224.00 MiB -> 24.06 MiB | hist: [ 59/ 291] blk.6.ffn_up.weight - [ 4096, 14336, 1, 1], type = f32, quantizing to q3_K .. size = 224.00 MiB -> 24.06 MiB | hist: [ 60/ 291] blk.6.ffn_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MB [ 61/ 291] blk.6.attn_k.weight - [ 4096, 1024, 1, 1], type = f32, quantizing to q3_K .. size = 16.00 MiB -> 1.72 MiB | hist: [ 62/ 291] blk.6.attn_output.weight - [ 4096, 4096, 1, 1], type = f32, quantizing to q4_K .. size = 64.00 MiB -> 9.00 MiB | hist: [ 63/ 291] blk.6.attn_q.weight - [ 4096, 4096, 1, 1], type = f32, quantizing to q3_K .. size = 64.00 MiB -> 6.88 MiB | hist: [ 64/ 291] blk.6.attn_v.weight - [ 4096, 1024, 1, 1], type = f32, quantizing to q4_K .. size = 16.00 MiB -> 2.25 MiB | hist: [ 65/ 291] blk.7.attn_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MB [ 66/ 291] blk.7.ffn_down.weight - [14336, 4096, 1, 1], type = f32, quantizing to q4_K .. size = 224.00 MiB -> 31.50 MiB | hist: [ 67/ 291] blk.7.ffn_gate.weight - [ 4096, 14336, 1, 1], type = f32, quantizing to q3_K .. size = 224.00 MiB -> 24.06 MiB | hist: [ 68/ 291] blk.7.ffn_up.weight - [ 4096, 14336, 1, 1], type = f32, quantizing to q3_K .. size = 224.00 MiB -> 24.06 MiB | hist: [ 69/ 291] blk.7.ffn_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MB [ 70/ 291] blk.7.attn_k.weight - [ 4096, 1024, 1, 1], type = f32, quantizing to q3_K .. size = 16.00 MiB -> 1.72 MiB | hist: [ 71/ 291] blk.7.attn_output.weight - [ 4096, 4096, 1, 1], type = f32, quantizing to q4_K .. size = 64.00 MiB -> 9.00 MiB | hist: [ 72/ 291] blk.7.attn_q.weight - [ 4096, 4096, 1, 1], type = f32, quantizing to q3_K .. size = 64.00 MiB -> 6.88 MiB | hist: [ 73/ 291] blk.7.attn_v.weight - [ 4096, 1024, 1, 1], type = f32, quantizing to q4_K .. size = 16.00 MiB -> 2.25 MiB | hist: [ 74/ 291] blk.8.attn_k.weight - [ 4096, 1024, 1, 1], type = f32, quantizing to q3_K .. size = 16.00 MiB -> 1.72 MiB | hist: [ 75/ 291] blk.8.attn_output.weight - [ 4096, 4096, 1, 1], type = f32, quantizing to q4_K .. size = 64.00 MiB -> 9.00 MiB | hist: [ 76/ 291] blk.8.attn_q.weight - [ 4096, 4096, 1, 1], type = f32, quantizing to q3_K .. size = 64.00 MiB -> 6.88 MiB | hist: [ 77/ 291] blk.8.attn_v.weight - [ 4096, 1024, 1, 1], type = f32, quantizing to q4_K .. size = 16.00 MiB -> 2.25 MiB | hist: [ 78/ 291] blk.10.attn_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MB [ 79/ 291] blk.10.ffn_down.weight - [14336, 4096, 1, 1], type = f32, quantizing to q4_K .. size = 224.00 MiB -> 31.50 MiB | hist: [ 80/ 291] blk.10.ffn_gate.weight - [ 4096, 14336, 1, 1], type = f32, quantizing to q3_K .. size = 224.00 MiB -> 24.06 MiB | hist: [ 81/ 291] blk.10.ffn_up.weight - [ 4096, 14336, 1, 1], type = f32, quantizing to q3_K .. size = 224.00 MiB -> 24.06 MiB | hist: [ 82/ 291] blk.10.ffn_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MB [ 83/ 291] blk.10.attn_k.weight - [ 4096, 1024, 1, 1], type = f32, quantizing to q3_K .. size = 16.00 MiB -> 1.72 MiB | hist: [ 84/ 291] blk.10.attn_output.weight - [ 4096, 4096, 1, 1], type = f32, quantizing to q4_K .. size = 64.00 MiB -> 9.00 MiB | hist: [ 85/ 291] blk.10.attn_q.weight - [ 4096, 4096, 1, 1], type = f32, quantizing to q3_K .. size = 64.00 MiB -> 6.88 MiB | hist: [ 86/ 291] blk.10.attn_v.weight - [ 4096, 1024, 1, 1], type = f32, quantizing to q4_K .. size = 16.00 MiB -> 2.25 MiB | hist: [ 87/ 291] blk.11.attn_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MB [ 88/ 291] blk.11.ffn_down.weight - [14336, 4096, 1, 1], type = f32, quantizing to q4_K .. size = 224.00 MiB -> 31.50 MiB | hist: [ 89/ 291] blk.11.ffn_gate.weight - [ 4096, 14336, 1, 1], type = f32, quantizing to q3_K .. size = 224.00 MiB -> 24.06 MiB | hist: [ 90/ 291] blk.11.ffn_up.weight - [ 4096, 14336, 1, 1], type = f32, quantizing to q3_K .. size = 224.00 MiB -> 24.06 MiB | hist: [ 91/ 291] blk.11.ffn_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MB [ 92/ 291] blk.11.attn_k.weight - [ 4096, 1024, 1, 1], type = f32, quantizing to q3_K .. size = 16.00 MiB -> 1.72 MiB | hist: [ 93/ 291] blk.11.attn_output.weight - [ 4096, 4096, 1, 1], type = f32, quantizing to q4_K .. size = 64.00 MiB -> 9.00 MiB | hist: [ 94/ 291] blk.11.attn_q.weight - [ 4096, 4096, 1, 1], type = f32, quantizing to q3_K .. size = 64.00 MiB -> 6.88 MiB | hist: [ 95/ 291] blk.11.attn_v.weight - [ 4096, 1024, 1, 1], type = f32, quantizing to q4_K .. size = 16.00 MiB -> 2.25 MiB | hist: [ 96/ 291] blk.12.ffn_gate.weight - [ 4096, 14336, 1, 1], type = f32, quantizing to q3_K .. size = 224.00 MiB -> 24.06 MiB | hist: [ 97/ 291] blk.12.ffn_up.weight - [ 4096, 14336, 1, 1], type = f32, quantizing to q3_K .. size = 224.00 MiB -> 24.06 MiB | hist: [ 98/ 291] blk.12.attn_k.weight - [ 4096, 1024, 1, 1], type = f32, quantizing to q3_K .. size = 16.00 MiB -> 1.72 MiB | hist: [ 99/ 291] blk.12.attn_output.weight - [ 4096, 4096, 1, 1], type = f32, quantizing to q4_K .. size = 64.00 MiB -> 9.00 MiB | hist: [ 100/ 291] blk.12.attn_q.weight - [ 4096, 4096, 1, 1], type = f32, quantizing to q3_K .. size = 64.00 MiB -> 6.88 MiB | hist: [ 101/ 291] blk.12.attn_v.weight - [ 4096, 1024, 1, 1], type = f32, quantizing to q4_K .. size = 16.00 MiB -> 2.25 MiB | hist: [ 102/ 291] blk.8.attn_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MB [ 103/ 291] blk.8.ffn_down.weight - [14336, 4096, 1, 1], type = f32, quantizing to q4_K .. size = 224.00 MiB -> 31.50 MiB | hist: [ 104/ 291] blk.8.ffn_gate.weight - [ 4096, 14336, 1, 1], type = f32, quantizing to q3_K .. size = 224.00 MiB -> 24.06 MiB | hist: [ 105/ 291] blk.8.ffn_up.weight - [ 4096, 14336, 1, 1], type = f32, quantizing to q3_K .. size = 224.00 MiB -> 24.06 MiB | hist: [ 106/ 291] blk.8.ffn_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MB [ 107/ 291] blk.9.attn_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MB [ 108/ 291] blk.9.ffn_down.weight - [14336, 4096, 1, 1], type = f32, quantizing to q4_K .. size = 224.00 MiB -> 31.50 MiB | hist: [ 109/ 291] blk.9.ffn_gate.weight - [ 4096, 14336, 1, 1], type = f32, quantizing to q3_K .. size = 224.00 MiB -> 24.06 MiB | hist: [ 110/ 291] blk.9.ffn_up.weight - [ 4096, 14336, 1, 1], type = f32, quantizing to q3_K .. size = 224.00 MiB -> 24.06 MiB | hist: [ 111/ 291] blk.9.ffn_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MB [ 112/ 291] blk.9.attn_k.weight - [ 4096, 1024, 1, 1], type = f32, quantizing to q3_K .. size = 16.00 MiB -> 1.72 MiB | hist: [ 113/ 291] blk.9.attn_output.weight - [ 4096, 4096, 1, 1], type = f32, quantizing to q4_K .. size = 64.00 MiB -> 9.00 MiB | hist: [ 114/ 291] blk.9.attn_q.weight - [ 4096, 4096, 1, 1], type = f32, quantizing to q3_K .. size = 64.00 MiB -> 6.88 MiB | hist: [ 115/ 291] blk.9.attn_v.weight - [ 4096, 1024, 1, 1], type = f32, quantizing to q4_K .. size = 16.00 MiB -> 2.25 MiB | hist: [ 116/ 291] blk.12.attn_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MB [ 117/ 291] blk.12.ffn_down.weight - [14336, 4096, 1, 1], type = f32, quantizing to q4_K .. size = 224.00 MiB -> 31.50 MiB | hist: [ 118/ 291] blk.12.ffn_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MB [ 119/ 291] blk.13.attn_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MB [ 120/ 291] blk.13.ffn_down.weight - [14336, 4096, 1, 1], type = f32, quantizing to q4_K .. size = 224.00 MiB -> 31.50 MiB | hist: [ 121/ 291] blk.13.ffn_gate.weight - [ 4096, 14336, 1, 1], type = f32, quantizing to q3_K .. size = 224.00 MiB -> 24.06 MiB | hist: [ 122/ 291] blk.13.ffn_up.weight - [ 4096, 14336, 1, 1], type = f32, quantizing to q3_K .. size = 224.00 MiB -> 24.06 MiB | hist: [ 123/ 291] blk.13.ffn_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MB [ 124/ 291] blk.13.attn_k.weight - [ 4096, 1024, 1, 1], type = f32, quantizing to q3_K .. size = 16.00 MiB -> 1.72 MiB | hist: [ 125/ 291] blk.13.attn_output.weight - [ 4096, 4096, 1, 1], type = f32, quantizing to q4_K .. size = 64.00 MiB -> 9.00 MiB | hist: [ 126/ 291] blk.13.attn_q.weight - [ 4096, 4096, 1, 1], type = f32, quantizing to q3_K .. size = 64.00 MiB -> 6.88 MiB | hist: [ 127/ 291] blk.13.attn_v.weight - [ 4096, 1024, 1, 1], type = f32, quantizing to q4_K .. size = 16.00 MiB -> 2.25 MiB | hist: [ 128/ 291] blk.14.attn_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MB [ 129/ 291] blk.14.ffn_down.weight - [14336, 4096, 1, 1], type = f32, quantizing to q4_K .. size = 224.00 MiB -> 31.50 MiB | hist: [ 130/ 291] blk.14.ffn_gate.weight - [ 4096, 14336, 1, 1], type = f32, quantizing to q3_K .. size = 224.00 MiB -> 24.06 MiB | hist: [ 131/ 291] blk.14.ffn_up.weight - [ 4096, 14336, 1, 1], type = f32, quantizing to q3_K .. size = 224.00 MiB -> 24.06 MiB | hist: [ 132/ 291] blk.14.ffn_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MB [ 133/ 291] blk.14.attn_k.weight - [ 4096, 1024, 1, 1], type = f32, quantizing to q3_K .. size = 16.00 MiB -> 1.72 MiB | hist: [ 134/ 291] blk.14.attn_output.weight - [ 4096, 4096, 1, 1], type = f32, quantizing to q4_K .. size = 64.00 MiB -> 9.00 MiB | hist: [ 135/ 291] blk.14.attn_q.weight - [ 4096, 4096, 1, 1], type = f32, quantizing to q3_K .. size = 64.00 MiB -> 6.88 MiB | hist: [ 136/ 291] blk.14.attn_v.weight - [ 4096, 1024, 1, 1], type = f32, quantizing to q4_K .. size = 16.00 MiB -> 2.25 MiB | hist: [ 137/ 291] blk.15.attn_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MB [ 138/ 291] blk.15.ffn_down.weight - [14336, 4096, 1, 1], type = f32, quantizing to q4_K .. size = 224.00 MiB -> 31.50 MiB | hist: [ 139/ 291] blk.15.ffn_gate.weight - [ 4096, 14336, 1, 1], type = f32, quantizing to q3_K .. size = 224.00 MiB -> 24.06 MiB | hist: [ 140/ 291] blk.15.ffn_up.weight - [ 4096, 14336, 1, 1], type = f32, quantizing to q3_K .. size = 224.00 MiB -> 24.06 MiB | hist: [ 141/ 291] blk.15.ffn_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MB [ 142/ 291] blk.15.attn_k.weight - [ 4096, 1024, 1, 1], type = f32, quantizing to q3_K .. size = 16.00 MiB -> 1.72 MiB | hist: [ 143/ 291] blk.15.attn_output.weight - [ 4096, 4096, 1, 1], type = f32, quantizing to q4_K .. size = 64.00 MiB -> 9.00 MiB | hist: [ 144/ 291] blk.15.attn_q.weight - [ 4096, 4096, 1, 1], type = f32, quantizing to q3_K .. size = 64.00 MiB -> 6.88 MiB | hist: [ 145/ 291] blk.15.attn_v.weight - [ 4096, 1024, 1, 1], type = f32, quantizing to q4_K .. size = 16.00 MiB -> 2.25 MiB | hist: [ 146/ 291] blk.16.attn_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MB [ 147/ 291] blk.16.ffn_down.weight - [14336, 4096, 1, 1], type = f32, quantizing to q4_K .. size = 224.00 MiB -> 31.50 MiB | hist: [ 148/ 291] blk.16.ffn_gate.weight - [ 4096, 14336, 1, 1], type = f32, quantizing to q3_K .. size = 224.00 MiB -> 24.06 MiB | hist: [ 149/ 291] blk.16.ffn_up.weight - [ 4096, 14336, 1, 1], type = f32, quantizing to q3_K .. size = 224.00 MiB -> 24.06 MiB | hist: [ 150/ 291] blk.16.ffn_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MB [ 151/ 291] blk.16.attn_k.weight - [ 4096, 1024, 1, 1], type = f32, quantizing to q3_K .. size = 16.00 MiB -> 1.72 MiB | hist: [ 152/ 291] blk.16.attn_output.weight - [ 4096, 4096, 1, 1], type = f32, quantizing to q4_K .. size = 64.00 MiB -> 9.00 MiB | hist: [ 153/ 291] blk.16.attn_q.weight - [ 4096, 4096, 1, 1], type = f32, quantizing to q3_K .. size = 64.00 MiB -> 6.88 MiB | hist: [ 154/ 291] blk.16.attn_v.weight - [ 4096, 1024, 1, 1], type = f32, quantizing to q4_K .. size = 16.00 MiB -> 2.25 MiB | hist: [ 155/ 291] blk.17.attn_k.weight - [ 4096, 1024, 1, 1], type = f32, quantizing to q3_K .. size = 16.00 MiB -> 1.72 MiB | hist: [ 156/ 291] blk.17.attn_output.weight - [ 4096, 4096, 1, 1], type = f32, quantizing to q4_K .. size = 64.00 MiB -> 9.00 MiB | hist: [ 157/ 291] blk.17.attn_q.weight - [ 4096, 4096, 1, 1], type = f32, quantizing to q3_K .. size = 64.00 MiB -> 6.88 MiB | hist: [ 158/ 291] blk.17.attn_v.weight - [ 4096, 1024, 1, 1], type = f32, quantizing to q4_K .. size = 16.00 MiB -> 2.25 MiB | hist: [ 159/ 291] blk.17.attn_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MB [ 160/ 291] blk.17.ffn_down.weight - [14336, 4096, 1, 1], type = f32, quantizing to q4_K .. size = 224.00 MiB -> 31.50 MiB | hist: [ 161/ 291] blk.17.ffn_gate.weight - [ 4096, 14336, 1, 1], type = f32, quantizing to q3_K .. size = 224.00 MiB -> 24.06 MiB | hist: [ 162/ 291] blk.17.ffn_up.weight - [ 4096, 14336, 1, 1], type = f32, quantizing to q3_K .. size = 224.00 MiB -> 24.06 MiB | hist: [ 163/ 291] blk.17.ffn_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MB [ 164/ 291] blk.18.attn_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MB [ 165/ 291] blk.18.ffn_down.weight - [14336, 4096, 1, 1], type = f32, quantizing to q4_K .. size = 224.00 MiB -> 31.50 MiB | hist: [ 166/ 291] blk.18.ffn_gate.weight - [ 4096, 14336, 1, 1], type = f32, quantizing to q3_K .. size = 224.00 MiB -> 24.06 MiB | hist: [ 167/ 291] blk.18.ffn_up.weight - [ 4096, 14336, 1, 1], type = f32, quantizing to q3_K .. size = 224.00 MiB -> 24.06 MiB | hist: [ 168/ 291] blk.18.ffn_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MB [ 169/ 291] blk.18.attn_k.weight - [ 4096, 1024, 1, 1], type = f32, quantizing to q3_K .. size = 16.00 MiB -> 1.72 MiB | hist: [ 170/ 291] blk.18.attn_output.weight - [ 4096, 4096, 1, 1], type = f32, quantizing to q4_K .. size = 64.00 MiB -> 9.00 MiB | hist: [ 171/ 291] blk.18.attn_q.weight - [ 4096, 4096, 1, 1], type = f32, quantizing to q3_K .. size = 64.00 MiB -> 6.88 MiB | hist: [ 172/ 291] blk.18.attn_v.weight - [ 4096, 1024, 1, 1], type = f32, quantizing to q4_K .. size = 16.00 MiB -> 2.25 MiB | hist: [ 173/ 291] blk.19.attn_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MB [ 174/ 291] blk.19.ffn_down.weight - [14336, 4096, 1, 1], type = f32, quantizing to q4_K .. size = 224.00 MiB -> 31.50 MiB | hist: [ 175/ 291] blk.19.ffn_gate.weight - [ 4096, 14336, 1, 1], type = f32, quantizing to q3_K .. size = 224.00 MiB -> 24.06 MiB | hist: [ 176/ 291] blk.19.ffn_up.weight - [ 4096, 14336, 1, 1], type = f32, quantizing to q3_K .. size = 224.00 MiB -> 24.06 MiB | hist: [ 177/ 291] blk.19.ffn_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MB [ 178/ 291] blk.19.attn_k.weight - [ 4096, 1024, 1, 1], type = f32, quantizing to q3_K .. size = 16.00 MiB -> 1.72 MiB | hist: [ 179/ 291] blk.19.attn_output.weight - [ 4096, 4096, 1, 1], type = f32, quantizing to q4_K .. size = 64.00 MiB -> 9.00 MiB | hist: [ 180/ 291] blk.19.attn_q.weight - [ 4096, 4096, 1, 1], type = f32, quantizing to q3_K .. size = 64.00 MiB -> 6.88 MiB | hist: [ 181/ 291] blk.19.attn_v.weight - [ 4096, 1024, 1, 1], type = f32, quantizing to q4_K .. size = 16.00 MiB -> 2.25 MiB | hist: [ 182/ 291] blk.20.attn_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MB [ 183/ 291] blk.20.ffn_down.weight - [14336, 4096, 1, 1], type = f32, quantizing to q4_K .. size = 224.00 MiB -> 31.50 MiB | hist: [ 184/ 291] blk.20.ffn_gate.weight - [ 4096, 14336, 1, 1], type = f32, quantizing to q3_K .. size = 224.00 MiB -> 24.06 MiB | hist: [ 185/ 291] blk.20.ffn_up.weight - [ 4096, 14336, 1, 1], type = f32, quantizing to q3_K .. size = 224.00 MiB -> 24.06 MiB | hist: [ 186/ 291] blk.20.ffn_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MB [ 187/ 291] blk.20.attn_k.weight - [ 4096, 1024, 1, 1], type = f32, quantizing to q3_K .. size = 16.00 MiB -> 1.72 MiB | hist: [ 188/ 291] blk.20.attn_output.weight - [ 4096, 4096, 1, 1], type = f32, quantizing to q4_K .. size = 64.00 MiB -> 9.00 MiB | hist: [ 189/ 291] blk.20.attn_q.weight - [ 4096, 4096, 1, 1], type = f32, quantizing to q3_K .. size = 64.00 MiB -> 6.88 MiB | hist: [ 190/ 291] blk.20.attn_v.weight - [ 4096, 1024, 1, 1], type = f32, quantizing to q4_K .. size = 16.00 MiB -> 2.25 MiB | hist: [ 191/ 291] blk.21.ffn_gate.weight - [ 4096, 14336, 1, 1], type = f32, quantizing to q3_K .. size = 224.00 MiB -> 24.06 MiB | hist: [ 192/ 291] blk.21.ffn_up.weight - [ 4096, 14336, 1, 1], type = f32, quantizing to q3_K .. size = 224.00 MiB -> 24.06 MiB | hist: [ 193/ 291] blk.21.attn_k.weight - [ 4096, 1024, 1, 1], type = f32, quantizing to q3_K .. size = 16.00 MiB -> 1.72 MiB | hist: [ 194/ 291] blk.21.attn_output.weight - [ 4096, 4096, 1, 1], type = f32, quantizing to q4_K .. size = 64.00 MiB -> 9.00 MiB | hist: [ 195/ 291] blk.21.attn_q.weight - [ 4096, 4096, 1, 1], type = f32, quantizing to q3_K .. size = 64.00 MiB -> 6.88 MiB | hist: [ 196/ 291] blk.21.attn_v.weight - [ 4096, 1024, 1, 1], type = f32, quantizing to q4_K .. size = 16.00 MiB -> 2.25 MiB | hist: [ 197/ 291] blk.21.attn_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MB [ 198/ 291] blk.21.ffn_down.weight - [14336, 4096, 1, 1], type = f32, quantizing to q4_K .. size = 224.00 MiB -> 31.50 MiB | hist: [ 199/ 291] blk.21.ffn_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MB [ 200/ 291] blk.22.attn_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MB [ 201/ 291] blk.22.ffn_down.weight - [14336, 4096, 1, 1], type = f32, quantizing to q4_K .. size = 224.00 MiB -> 31.50 MiB | hist: [ 202/ 291] blk.22.ffn_gate.weight - [ 4096, 14336, 1, 1], type = f32, quantizing to q3_K .. size = 224.00 MiB -> 24.06 MiB | hist: [ 203/ 291] blk.22.ffn_up.weight - [ 4096, 14336, 1, 1], type = f32, quantizing to q3_K .. size = 224.00 MiB -> 24.06 MiB | hist: [ 204/ 291] blk.22.ffn_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MB [ 205/ 291] blk.22.attn_k.weight - [ 4096, 1024, 1, 1], type = f32, quantizing to q3_K .. size = 16.00 MiB -> 1.72 MiB | hist: [ 206/ 291] blk.22.attn_output.weight - [ 4096, 4096, 1, 1], type = f32, quantizing to q4_K .. size = 64.00 MiB -> 9.00 MiB | hist: [ 207/ 291] blk.22.attn_q.weight - [ 4096, 4096, 1, 1], type = f32, quantizing to q3_K .. size = 64.00 MiB -> 6.88 MiB | hist: [ 208/ 291] blk.22.attn_v.weight - [ 4096, 1024, 1, 1], type = f32, quantizing to q4_K .. size = 16.00 MiB -> 2.25 MiB | hist: [ 209/ 291] blk.23.attn_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MB [ 210/ 291] blk.23.ffn_down.weight - [14336, 4096, 1, 1], type = f32, quantizing to q4_K .. size = 224.00 MiB -> 31.50 MiB | hist: [ 211/ 291] blk.23.ffn_gate.weight - [ 4096, 14336, 1, 1], type = f32, quantizing to q3_K .. size = 224.00 MiB -> 24.06 MiB | hist: [ 212/ 291] blk.23.ffn_up.weight - [ 4096, 14336, 1, 1], type = f32, quantizing to q3_K .. size = 224.00 MiB -> 24.06 MiB | hist: [ 213/ 291] blk.23.ffn_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MB [ 214/ 291] blk.23.attn_k.weight - [ 4096, 1024, 1, 1], type = f32, quantizing to q3_K .. size = 16.00 MiB -> 1.72 MiB | hist: [ 215/ 291] blk.23.attn_output.weight - [ 4096, 4096, 1, 1], type = f32, quantizing to q4_K .. size = 64.00 MiB -> 9.00 MiB | hist: [ 216/ 291] blk.23.attn_q.weight - [ 4096, 4096, 1, 1], type = f32, quantizing to q3_K .. size = 64.00 MiB -> 6.88 MiB | hist: [ 217/ 291] blk.23.attn_v.weight - [ 4096, 1024, 1, 1], type = f32, quantizing to q4_K .. size = 16.00 MiB -> 2.25 MiB | hist: [ 218/ 291] blk.24.attn_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MB [ 219/ 291] blk.24.ffn_down.weight - [14336, 4096, 1, 1], type = f32, quantizing to q4_K .. size = 224.00 MiB -> 31.50 MiB | hist: [ 220/ 291] blk.24.ffn_gate.weight - [ 4096, 14336, 1, 1], type = f32, quantizing to q3_K .. size = 224.00 MiB -> 24.06 MiB | hist: [ 221/ 291] blk.24.ffn_up.weight - [ 4096, 14336, 1, 1], type = f32, quantizing to q3_K .. size = 224.00 MiB -> 24.06 MiB | hist: [ 222/ 291] blk.24.ffn_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MB [ 223/ 291] blk.24.attn_k.weight - [ 4096, 1024, 1, 1], type = f32, quantizing to q3_K .. size = 16.00 MiB -> 1.72 MiB | hist: [ 224/ 291] blk.24.attn_output.weight - [ 4096, 4096, 1, 1], type = f32, quantizing to q4_K .. size = 64.00 MiB -> 9.00 MiB | hist: [ 225/ 291] blk.24.attn_q.weight - [ 4096, 4096, 1, 1], type = f32, quantizing to q3_K .. size = 64.00 MiB -> 6.88 MiB | hist: [ 226/ 291] blk.24.attn_v.weight - [ 4096, 1024, 1, 1], type = f32, quantizing to q4_K .. size = 16.00 MiB -> 2.25 MiB | hist: [ 227/ 291] blk.25.attn_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MB [ 228/ 291] blk.25.ffn_down.weight - [14336, 4096, 1, 1], type = f32, quantizing to q4_K .. size = 224.00 MiB -> 31.50 MiB | hist: [ 229/ 291] blk.25.ffn_gate.weight - [ 4096, 14336, 1, 1], type = f32, quantizing to q3_K .. size = 224.00 MiB -> 24.06 MiB | hist: [ 230/ 291] blk.25.ffn_up.weight - [ 4096, 14336, 1, 1], type = f32, quantizing to q3_K .. size = 224.00 MiB -> 24.06 MiB | hist: [ 231/ 291] blk.25.ffn_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MB [ 232/ 291] blk.25.attn_k.weight - [ 4096, 1024, 1, 1], type = f32, quantizing to q3_K .. size = 16.00 MiB -> 1.72 MiB | hist: [ 233/ 291] blk.25.attn_output.weight - [ 4096, 4096, 1, 1], type = f32, quantizing to q4_K .. size = 64.00 MiB -> 9.00 MiB | hist: [ 234/ 291] blk.25.attn_q.weight - [ 4096, 4096, 1, 1], type = f32, quantizing to q3_K .. size = 64.00 MiB -> 6.88 MiB | hist: [ 235/ 291] blk.25.attn_v.weight - [ 4096, 1024, 1, 1], type = f32, quantizing to q4_K .. size = 16.00 MiB -> 2.25 MiB | hist: [ 236/ 291] blk.26.attn_k.weight - [ 4096, 1024, 1, 1], type = f32, quantizing to q3_K .. size = 16.00 MiB -> 1.72 MiB | hist: [ 237/ 291] blk.26.attn_output.weight - [ 4096, 4096, 1, 1], type = f32, quantizing to q4_K .. size = 64.00 MiB -> 9.00 MiB | hist: [ 238/ 291] blk.26.attn_q.weight - [ 4096, 4096, 1, 1], type = f32, quantizing to q3_K .. size = 64.00 MiB -> 6.88 MiB | hist: [ 239/ 291] blk.26.attn_v.weight - [ 4096, 1024, 1, 1], type = f32, quantizing to q4_K .. size = 16.00 MiB -> 2.25 MiB | hist: [ 240/ 291] blk.26.attn_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MB [ 241/ 291] blk.26.ffn_down.weight - [14336, 4096, 1, 1], type = f32, quantizing to q4_K .. size = 224.00 MiB -> 31.50 MiB | hist: [ 242/ 291] blk.26.ffn_gate.weight - [ 4096, 14336, 1, 1], type = f32, quantizing to q3_K .. size = 224.00 MiB -> 24.06 MiB | hist: [ 243/ 291] blk.26.ffn_up.weight - [ 4096, 14336, 1, 1], type = f32, quantizing to q3_K .. size = 224.00 MiB -> 24.06 MiB | hist: [ 244/ 291] blk.26.ffn_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MB [ 245/ 291] blk.27.attn_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MB [ 246/ 291] blk.27.ffn_down.weight - [14336, 4096, 1, 1], type = f32, quantizing to q4_K .. size = 224.00 MiB -> 31.50 MiB | hist: [ 247/ 291] blk.27.ffn_gate.weight - [ 4096, 14336, 1, 1], type = f32, quantizing to q3_K .. size = 224.00 MiB -> 24.06 MiB | hist: [ 248/ 291] blk.27.ffn_up.weight - [ 4096, 14336, 1, 1], type = f32, quantizing to q3_K .. size = 224.00 MiB -> 24.06 MiB | hist: [ 249/ 291] blk.27.ffn_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MB [ 250/ 291] blk.27.attn_k.weight - [ 4096, 1024, 1, 1], type = f32, quantizing to q3_K .. size = 16.00 MiB -> 1.72 MiB | hist: [ 251/ 291] blk.27.attn_output.weight - [ 4096, 4096, 1, 1], type = f32, quantizing to q4_K .. size = 64.00 MiB -> 9.00 MiB | hist: [ 252/ 291] blk.27.attn_q.weight - [ 4096, 4096, 1, 1], type = f32, quantizing to q3_K .. size = 64.00 MiB -> 6.88 MiB | hist: [ 253/ 291] blk.27.attn_v.weight - [ 4096, 1024, 1, 1], type = f32, quantizing to q4_K .. size = 16.00 MiB -> 2.25 MiB | hist: [ 254/ 291] blk.28.attn_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MB [ 255/ 291] blk.28.ffn_down.weight - [14336, 4096, 1, 1], type = f32, quantizing to q4_K .. size = 224.00 MiB -> 31.50 MiB | hist: [ 256/ 291] blk.28.ffn_gate.weight - [ 4096, 14336, 1, 1], type = f32, quantizing to q3_K .. size = 224.00 MiB -> 24.06 MiB | hist: [ 257/ 291] blk.28.ffn_up.weight - [ 4096, 14336, 1, 1], type = f32, quantizing to q3_K .. size = 224.00 MiB -> 24.06 MiB | hist: [ 258/ 291] blk.28.ffn_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MB [ 259/ 291] blk.28.attn_k.weight - [ 4096, 1024, 1, 1], type = f32, quantizing to q3_K .. size = 16.00 MiB -> 1.72 MiB | hist: [ 260/ 291] blk.28.attn_output.weight - [ 4096, 4096, 1, 1], type = f32, quantizing to q4_K .. size = 64.00 MiB -> 9.00 MiB | hist: [ 261/ 291] blk.28.attn_q.weight - [ 4096, 4096, 1, 1], type = f32, quantizing to q3_K .. size = 64.00 MiB -> 6.88 MiB | hist: [ 262/ 291] blk.28.attn_v.weight - [ 4096, 1024, 1, 1], type = f32, quantizing to q4_K .. size = 16.00 MiB -> 2.25 MiB | hist: [ 263/ 291] blk.29.attn_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MB [ 264/ 291] blk.29.ffn_down.weight - [14336, 4096, 1, 1], type = f32, quantizing to q4_K .. size = 224.00 MiB -> 31.50 MiB | hist: [ 265/ 291] blk.29.ffn_gate.weight - [ 4096, 14336, 1, 1], type = f32, quantizing to q3_K .. size = 224.00 MiB -> 24.06 MiB | hist: [ 266/ 291] blk.29.ffn_up.weight - [ 4096, 14336, 1, 1], type = f32, quantizing to q3_K .. size = 224.00 MiB -> 24.06 MiB | hist: [ 267/ 291] blk.29.ffn_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MB [ 268/ 291] blk.29.attn_k.weight - [ 4096, 1024, 1, 1], type = f32, quantizing to q3_K .. size = 16.00 MiB -> 1.72 MiB | hist: [ 269/ 291] blk.29.attn_output.weight - [ 4096, 4096, 1, 1], type = f32, quantizing to q4_K .. size = 64.00 MiB -> 9.00 MiB | hist: [ 270/ 291] blk.29.attn_q.weight - [ 4096, 4096, 1, 1], type = f32, quantizing to q3_K .. size = 64.00 MiB -> 6.88 MiB | hist: [ 271/ 291] blk.29.attn_v.weight - [ 4096, 1024, 1, 1], type = f32, quantizing to q4_K .. size = 16.00 MiB -> 2.25 MiB | hist: [ 272/ 291] blk.30.ffn_gate.weight - [ 4096, 14336, 1, 1], type = f32, quantizing to q3_K .. size = 224.00 MiB -> 24.06 MiB | hist: [ 273/ 291] blk.30.ffn_up.weight - [ 4096, 14336, 1, 1], type = f32, quantizing to q3_K .. size = 224.00 MiB -> 24.06 MiB | hist: [ 274/ 291] blk.30.attn_k.weight - [ 4096, 1024, 1, 1], type = f32, quantizing to q3_K .. size = 16.00 MiB -> 1.72 MiB | hist: [ 275/ 291] blk.30.attn_output.weight - [ 4096, 4096, 1, 1], type = f32, quantizing to q4_K .. size = 64.00 MiB -> 9.00 MiB | hist: [ 276/ 291] blk.30.attn_q.weight - [ 4096, 4096, 1, 1], type = f32, quantizing to q3_K .. size = 64.00 MiB -> 6.88 MiB | hist: [ 277/ 291] blk.30.attn_v.weight - [ 4096, 1024, 1, 1], type = f32, quantizing to q4_K .. size = 16.00 MiB -> 2.25 MiB | hist: [ 278/ 291] output.weight - [ 4096, 32000, 1, 1], type = f32, quantizing to q6_K .. size = 500.00 MiB -> 102.54 MiB | hist: [ 279/ 291] blk.30.attn_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MB [ 280/ 291] blk.30.ffn_down.weight - [14336, 4096, 1, 1], type = f32, quantizing to q4_K .. size = 224.00 MiB -> 31.50 MiB | hist: [ 281/ 291] blk.30.ffn_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MB [ 282/ 291] blk.31.attn_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MB [ 283/ 291] blk.31.ffn_down.weight - [14336, 4096, 1, 1], type = f32, quantizing to q4_K .. size = 224.00 MiB -> 31.50 MiB | hist: [ 284/ 291] blk.31.ffn_gate.weight - [ 4096, 14336, 1, 1], type = f32, quantizing to q3_K .. size = 224.00 MiB -> 24.06 MiB | hist: [ 285/ 291] blk.31.ffn_up.weight - [ 4096, 14336, 1, 1], type = f32, quantizing to q3_K .. size = 224.00 MiB -> 24.06 MiB | hist: [ 286/ 291] blk.31.ffn_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MB [ 287/ 291] blk.31.attn_k.weight - [ 4096, 1024, 1, 1], type = f32, quantizing to q3_K .. size = 16.00 MiB -> 1.72 MiB | hist: [ 288/ 291] blk.31.attn_output.weight - [ 4096, 4096, 1, 1], type = f32, quantizing to q4_K .. size = 64.00 MiB -> 9.00 MiB | hist: [ 289/ 291] blk.31.attn_q.weight - [ 4096, 4096, 1, 1], type = f32, quantizing to q3_K .. size = 64.00 MiB -> 6.88 MiB | hist: [ 290/ 291] blk.31.attn_v.weight - [ 4096, 1024, 1, 1], type = f32, quantizing to q4_K .. size = 16.00 MiB -> 2.25 MiB | hist: [ 291/ 291] output_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MB llama_model_quantize_internal: model size = 27625.02 MB llama_model_quantize_internal: quant size = 3355.27 MB main: quantize time = 368785.09 ms main: total time = 368785.09 ms