mradermacher commited on
Commit
0fcec47
1 Parent(s): 8e10fc1

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +13 -0
README.md CHANGED
@@ -37,13 +37,26 @@ more details, including on how to concatenate multi-part files.
37
 
38
  | Link | Type | Size/GB | Notes |
39
  |:-----|:-----|--------:|:------|
 
 
 
 
 
40
  | [GGUF](https://huggingface.co/mradermacher/Llama-3.2-SUN-1B-chat-i1-GGUF/resolve/main/Llama-3.2-SUN-1B-chat.i1-IQ2_M.gguf) | i1-IQ2_M | 0.7 | |
41
  | [GGUF](https://huggingface.co/mradermacher/Llama-3.2-SUN-1B-chat-i1-GGUF/resolve/main/Llama-3.2-SUN-1B-chat.i1-Q2_K.gguf) | i1-Q2_K | 0.8 | IQ3_XXS probably better |
42
  | [GGUF](https://huggingface.co/mradermacher/Llama-3.2-SUN-1B-chat-i1-GGUF/resolve/main/Llama-3.2-SUN-1B-chat.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 0.8 | lower quality |
 
 
 
43
  | [GGUF](https://huggingface.co/mradermacher/Llama-3.2-SUN-1B-chat-i1-GGUF/resolve/main/Llama-3.2-SUN-1B-chat.i1-IQ3_M.gguf) | i1-IQ3_M | 0.9 | |
44
  | [GGUF](https://huggingface.co/mradermacher/Llama-3.2-SUN-1B-chat-i1-GGUF/resolve/main/Llama-3.2-SUN-1B-chat.i1-Q3_K_M.gguf) | i1-Q3_K_M | 0.9 | IQ3_S probably better |
 
 
 
45
  | [GGUF](https://huggingface.co/mradermacher/Llama-3.2-SUN-1B-chat-i1-GGUF/resolve/main/Llama-3.2-SUN-1B-chat.i1-Q4_K_S.gguf) | i1-Q4_K_S | 1.0 | optimal size/speed/quality |
46
  | [GGUF](https://huggingface.co/mradermacher/Llama-3.2-SUN-1B-chat-i1-GGUF/resolve/main/Llama-3.2-SUN-1B-chat.i1-Q4_K_M.gguf) | i1-Q4_K_M | 1.1 | fast, recommended |
 
 
47
  | [GGUF](https://huggingface.co/mradermacher/Llama-3.2-SUN-1B-chat-i1-GGUF/resolve/main/Llama-3.2-SUN-1B-chat.i1-Q6_K.gguf) | i1-Q6_K | 1.3 | practically like static Q6_K |
48
 
49
  Here is a handy graph by ikawrakow comparing some lower-quality quant
 
37
 
38
  | Link | Type | Size/GB | Notes |
39
  |:-----|:-----|--------:|:------|
40
+ | [GGUF](https://huggingface.co/mradermacher/Llama-3.2-SUN-1B-chat-i1-GGUF/resolve/main/Llama-3.2-SUN-1B-chat.i1-IQ1_S.gguf) | i1-IQ1_S | 0.6 | for the desperate |
41
+ | [GGUF](https://huggingface.co/mradermacher/Llama-3.2-SUN-1B-chat-i1-GGUF/resolve/main/Llama-3.2-SUN-1B-chat.i1-IQ1_M.gguf) | i1-IQ1_M | 0.6 | mostly desperate |
42
+ | [GGUF](https://huggingface.co/mradermacher/Llama-3.2-SUN-1B-chat-i1-GGUF/resolve/main/Llama-3.2-SUN-1B-chat.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 0.6 | |
43
+ | [GGUF](https://huggingface.co/mradermacher/Llama-3.2-SUN-1B-chat-i1-GGUF/resolve/main/Llama-3.2-SUN-1B-chat.i1-IQ2_XS.gguf) | i1-IQ2_XS | 0.7 | |
44
+ | [GGUF](https://huggingface.co/mradermacher/Llama-3.2-SUN-1B-chat-i1-GGUF/resolve/main/Llama-3.2-SUN-1B-chat.i1-IQ2_S.gguf) | i1-IQ2_S | 0.7 | |
45
  | [GGUF](https://huggingface.co/mradermacher/Llama-3.2-SUN-1B-chat-i1-GGUF/resolve/main/Llama-3.2-SUN-1B-chat.i1-IQ2_M.gguf) | i1-IQ2_M | 0.7 | |
46
  | [GGUF](https://huggingface.co/mradermacher/Llama-3.2-SUN-1B-chat-i1-GGUF/resolve/main/Llama-3.2-SUN-1B-chat.i1-Q2_K.gguf) | i1-Q2_K | 0.8 | IQ3_XXS probably better |
47
  | [GGUF](https://huggingface.co/mradermacher/Llama-3.2-SUN-1B-chat-i1-GGUF/resolve/main/Llama-3.2-SUN-1B-chat.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 0.8 | lower quality |
48
+ | [GGUF](https://huggingface.co/mradermacher/Llama-3.2-SUN-1B-chat-i1-GGUF/resolve/main/Llama-3.2-SUN-1B-chat.i1-IQ3_XS.gguf) | i1-IQ3_XS | 0.8 | |
49
+ | [GGUF](https://huggingface.co/mradermacher/Llama-3.2-SUN-1B-chat-i1-GGUF/resolve/main/Llama-3.2-SUN-1B-chat.i1-Q3_K_S.gguf) | i1-Q3_K_S | 0.9 | IQ3_XS probably better |
50
+ | [GGUF](https://huggingface.co/mradermacher/Llama-3.2-SUN-1B-chat-i1-GGUF/resolve/main/Llama-3.2-SUN-1B-chat.i1-IQ3_S.gguf) | i1-IQ3_S | 0.9 | beats Q3_K* |
51
  | [GGUF](https://huggingface.co/mradermacher/Llama-3.2-SUN-1B-chat-i1-GGUF/resolve/main/Llama-3.2-SUN-1B-chat.i1-IQ3_M.gguf) | i1-IQ3_M | 0.9 | |
52
  | [GGUF](https://huggingface.co/mradermacher/Llama-3.2-SUN-1B-chat-i1-GGUF/resolve/main/Llama-3.2-SUN-1B-chat.i1-Q3_K_M.gguf) | i1-Q3_K_M | 0.9 | IQ3_S probably better |
53
+ | [GGUF](https://huggingface.co/mradermacher/Llama-3.2-SUN-1B-chat-i1-GGUF/resolve/main/Llama-3.2-SUN-1B-chat.i1-Q3_K_L.gguf) | i1-Q3_K_L | 0.9 | IQ3_M probably better |
54
+ | [GGUF](https://huggingface.co/mradermacher/Llama-3.2-SUN-1B-chat-i1-GGUF/resolve/main/Llama-3.2-SUN-1B-chat.i1-IQ4_XS.gguf) | i1-IQ4_XS | 1.0 | |
55
+ | [GGUF](https://huggingface.co/mradermacher/Llama-3.2-SUN-1B-chat-i1-GGUF/resolve/main/Llama-3.2-SUN-1B-chat.i1-Q4_0.gguf) | i1-Q4_0 | 1.0 | fast, low quality |
56
  | [GGUF](https://huggingface.co/mradermacher/Llama-3.2-SUN-1B-chat-i1-GGUF/resolve/main/Llama-3.2-SUN-1B-chat.i1-Q4_K_S.gguf) | i1-Q4_K_S | 1.0 | optimal size/speed/quality |
57
  | [GGUF](https://huggingface.co/mradermacher/Llama-3.2-SUN-1B-chat-i1-GGUF/resolve/main/Llama-3.2-SUN-1B-chat.i1-Q4_K_M.gguf) | i1-Q4_K_M | 1.1 | fast, recommended |
58
+ | [GGUF](https://huggingface.co/mradermacher/Llama-3.2-SUN-1B-chat-i1-GGUF/resolve/main/Llama-3.2-SUN-1B-chat.i1-Q5_K_S.gguf) | i1-Q5_K_S | 1.2 | |
59
+ | [GGUF](https://huggingface.co/mradermacher/Llama-3.2-SUN-1B-chat-i1-GGUF/resolve/main/Llama-3.2-SUN-1B-chat.i1-Q5_K_M.gguf) | i1-Q5_K_M | 1.2 | |
60
  | [GGUF](https://huggingface.co/mradermacher/Llama-3.2-SUN-1B-chat-i1-GGUF/resolve/main/Llama-3.2-SUN-1B-chat.i1-Q6_K.gguf) | i1-Q6_K | 1.3 | practically like static Q6_K |
61
 
62
  Here is a handy graph by ikawrakow comparing some lower-quality quant