localmodels/WizardLM-30B-v1.0-ggml

WizardLM 30B v1.0 ggml

From: https://huggingface.co/WizardLM/WizardLM-30B-V1.0

---

Original llama.cpp quant methods: q4_0, q4_1, q5_0, q5_1, q8_0

Quantized using an older version of llama.cpp and compatible with llama.cpp from May 19, commit 2d5db48.

k-quant methods: q2_K, q3_K_S, q3_K_M, q3_K_L, q4_K_S, q4_K_M, q5_K_S, q6_K

Quantization methods compatible with latest llama.cpp from June 6, commit 2d43387.

---

Files

Name	Quant method	Bits	Size	Max RAM required, no GPU offloading	Use case
wizardlm-30b.ggmlv3.q2_K.bin	q2_K	2	13.60 GB	16.10 GB	New k-quant method. Uses GGML_TYPE_Q4_K for the attention.vw and feed_forward.w2 tensors, GGML_TYPE_Q2_K for the other tensors.
wizardlm-30b.ggmlv3.q3_K_L.bin	q3_K_L	3	17.20 GB	19.70 GB	New k-quant method. Uses GGML_TYPE_Q5_K for the attention.wv, attention.wo, and feed_forward.w2 tensors, else GGML_TYPE_Q3_K
wizardlm-30b.ggmlv3.q3_K_M.bin	q3_K_M	3	15.64 GB	18.14 GB	New k-quant method. Uses GGML_TYPE_Q4_K for the attention.wv, attention.wo, and feed_forward.w2 tensors, else GGML_TYPE_Q3_K
wizardlm-30b.ggmlv3.q3_K_S.bin	q3_K_S	3	13.98 GB	16.48 GB	New k-quant method. Uses GGML_TYPE_Q3_K for all tensors
wizardlm-30b.ggmlv3.q4_0.bin	q4_0	4	18.30 GB	20.80 GB	Original llama.cpp quant method, 4-bit.
wizardlm-30b.ggmlv3.q4_1.bin	q4_1	4	20.33 GB	22.83 GB	Original llama.cpp quant method, 4-bit. Higher accuracy than q4_0 but not as high as q5_0. However has quicker inference than q5 models.
wizardlm-30b.ggmlv3.q4_K_M.bin	q4_K_M	4	19.57 GB	22.07 GB	New k-quant method. Uses GGML_TYPE_Q6_K for half of the attention.wv and feed_forward.w2 tensors, else GGML_TYPE_Q4_K
wizardlm-30b.ggmlv3.q4_K_S.bin	q4_K_S	4	18.30 GB	20.80 GB	New k-quant method. Uses GGML_TYPE_Q4_K for all tensors
wizardlm-30b.ggmlv3.q5_0.bin	q5_0	5	22.37 GB	24.87 GB	Original llama.cpp quant method, 5-bit. Higher accuracy, higher resource usage and slower inference.
wizardlm-30b.ggmlv3.q5_1.bin	q5_1	5	24.40 GB	26.90 GB	Original llama.cpp quant method, 5-bit. Even higher accuracy, resource usage and slower inference.
wizardlm-30b.ggmlv3.q5_K_M.bin	q5_K_M	5	23.02 GB	25.52 GB	New k-quant method. Uses GGML_TYPE_Q6_K for half of the attention.wv and feed_forward.w2 tensors, else GGML_TYPE_Q5_K
wizardlm-30b.ggmlv3.q5_K_S.bin	q5_K_S	5	22.37 GB	24.87 GB	New k-quant method. Uses GGML_TYPE_Q5_K for all tensors
wizardlm-30b.ggmlv3.q6_K.bin	q6_K	6	26.69 GB	29.19 GB	New k-quant method. Uses GGML_TYPE_Q8_K - 6-bit quantization - for all tensors
wizardlm-30b.ggmlv3.q8_0.bin	q8_0	8	34.56 GB	37.06 GB	Original llama.cpp quant method, 8-bit. Almost indistinguishable from float16. High resource use and slow. Not recommended for most users.