mradermacher commited on
Commit
21912fa
·
verified ·
1 Parent(s): d7d9709

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +9 -0
README.md CHANGED
@@ -28,19 +28,28 @@ more details, including on how to concatenate multi-part files.
28
 
29
  | Link | Type | Size/GB | Notes |
30
  |:-----|:-----|--------:|:------|
 
31
  | [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-Distill-Qwen-32B-i1-GGUF/resolve/main/DeepSeek-R1-Distill-Qwen-32B.i1-IQ1_M.gguf) | i1-IQ1_M | 8.0 | mostly desperate |
32
  | [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-Distill-Qwen-32B-i1-GGUF/resolve/main/DeepSeek-R1-Distill-Qwen-32B.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 9.1 | |
 
 
33
  | [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-Distill-Qwen-32B-i1-GGUF/resolve/main/DeepSeek-R1-Distill-Qwen-32B.i1-IQ2_M.gguf) | i1-IQ2_M | 11.4 | |
34
  | [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-Distill-Qwen-32B-i1-GGUF/resolve/main/DeepSeek-R1-Distill-Qwen-32B.i1-Q2_K_S.gguf) | i1-Q2_K_S | 11.6 | very low quality |
35
  | [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-Distill-Qwen-32B-i1-GGUF/resolve/main/DeepSeek-R1-Distill-Qwen-32B.i1-Q2_K.gguf) | i1-Q2_K | 12.4 | IQ3_XXS probably better |
36
  | [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-Distill-Qwen-32B-i1-GGUF/resolve/main/DeepSeek-R1-Distill-Qwen-32B.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 12.9 | lower quality |
 
37
  | [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-Distill-Qwen-32B-i1-GGUF/resolve/main/DeepSeek-R1-Distill-Qwen-32B.i1-Q3_K_S.gguf) | i1-Q3_K_S | 14.5 | IQ3_XS probably better |
 
38
  | [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-Distill-Qwen-32B-i1-GGUF/resolve/main/DeepSeek-R1-Distill-Qwen-32B.i1-IQ3_M.gguf) | i1-IQ3_M | 14.9 | |
39
  | [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-Distill-Qwen-32B-i1-GGUF/resolve/main/DeepSeek-R1-Distill-Qwen-32B.i1-Q3_K_M.gguf) | i1-Q3_K_M | 16.0 | IQ3_S probably better |
40
  | [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-Distill-Qwen-32B-i1-GGUF/resolve/main/DeepSeek-R1-Distill-Qwen-32B.i1-Q3_K_L.gguf) | i1-Q3_K_L | 17.3 | IQ3_M probably better |
41
  | [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-Distill-Qwen-32B-i1-GGUF/resolve/main/DeepSeek-R1-Distill-Qwen-32B.i1-IQ4_XS.gguf) | i1-IQ4_XS | 17.8 | |
 
42
  | [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-Distill-Qwen-32B-i1-GGUF/resolve/main/DeepSeek-R1-Distill-Qwen-32B.i1-Q4_K_S.gguf) | i1-Q4_K_S | 18.9 | optimal size/speed/quality |
43
  | [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-Distill-Qwen-32B-i1-GGUF/resolve/main/DeepSeek-R1-Distill-Qwen-32B.i1-Q4_K_M.gguf) | i1-Q4_K_M | 20.0 | fast, recommended |
 
 
 
44
  | [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-Distill-Qwen-32B-i1-GGUF/resolve/main/DeepSeek-R1-Distill-Qwen-32B.i1-Q6_K.gguf) | i1-Q6_K | 27.0 | practically like static Q6_K |
45
 
46
  Here is a handy graph by ikawrakow comparing some lower-quality quant
 
28
 
29
  | Link | Type | Size/GB | Notes |
30
  |:-----|:-----|--------:|:------|
31
+ | [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-Distill-Qwen-32B-i1-GGUF/resolve/main/DeepSeek-R1-Distill-Qwen-32B.i1-IQ1_S.gguf) | i1-IQ1_S | 7.4 | for the desperate |
32
  | [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-Distill-Qwen-32B-i1-GGUF/resolve/main/DeepSeek-R1-Distill-Qwen-32B.i1-IQ1_M.gguf) | i1-IQ1_M | 8.0 | mostly desperate |
33
  | [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-Distill-Qwen-32B-i1-GGUF/resolve/main/DeepSeek-R1-Distill-Qwen-32B.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 9.1 | |
34
+ | [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-Distill-Qwen-32B-i1-GGUF/resolve/main/DeepSeek-R1-Distill-Qwen-32B.i1-IQ2_XS.gguf) | i1-IQ2_XS | 10.1 | |
35
+ | [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-Distill-Qwen-32B-i1-GGUF/resolve/main/DeepSeek-R1-Distill-Qwen-32B.i1-IQ2_S.gguf) | i1-IQ2_S | 10.5 | |
36
  | [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-Distill-Qwen-32B-i1-GGUF/resolve/main/DeepSeek-R1-Distill-Qwen-32B.i1-IQ2_M.gguf) | i1-IQ2_M | 11.4 | |
37
  | [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-Distill-Qwen-32B-i1-GGUF/resolve/main/DeepSeek-R1-Distill-Qwen-32B.i1-Q2_K_S.gguf) | i1-Q2_K_S | 11.6 | very low quality |
38
  | [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-Distill-Qwen-32B-i1-GGUF/resolve/main/DeepSeek-R1-Distill-Qwen-32B.i1-Q2_K.gguf) | i1-Q2_K | 12.4 | IQ3_XXS probably better |
39
  | [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-Distill-Qwen-32B-i1-GGUF/resolve/main/DeepSeek-R1-Distill-Qwen-32B.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 12.9 | lower quality |
40
+ | [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-Distill-Qwen-32B-i1-GGUF/resolve/main/DeepSeek-R1-Distill-Qwen-32B.i1-IQ3_XS.gguf) | i1-IQ3_XS | 13.8 | |
41
  | [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-Distill-Qwen-32B-i1-GGUF/resolve/main/DeepSeek-R1-Distill-Qwen-32B.i1-Q3_K_S.gguf) | i1-Q3_K_S | 14.5 | IQ3_XS probably better |
42
+ | [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-Distill-Qwen-32B-i1-GGUF/resolve/main/DeepSeek-R1-Distill-Qwen-32B.i1-IQ3_S.gguf) | i1-IQ3_S | 14.5 | beats Q3_K* |
43
  | [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-Distill-Qwen-32B-i1-GGUF/resolve/main/DeepSeek-R1-Distill-Qwen-32B.i1-IQ3_M.gguf) | i1-IQ3_M | 14.9 | |
44
  | [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-Distill-Qwen-32B-i1-GGUF/resolve/main/DeepSeek-R1-Distill-Qwen-32B.i1-Q3_K_M.gguf) | i1-Q3_K_M | 16.0 | IQ3_S probably better |
45
  | [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-Distill-Qwen-32B-i1-GGUF/resolve/main/DeepSeek-R1-Distill-Qwen-32B.i1-Q3_K_L.gguf) | i1-Q3_K_L | 17.3 | IQ3_M probably better |
46
  | [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-Distill-Qwen-32B-i1-GGUF/resolve/main/DeepSeek-R1-Distill-Qwen-32B.i1-IQ4_XS.gguf) | i1-IQ4_XS | 17.8 | |
47
+ | [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-Distill-Qwen-32B-i1-GGUF/resolve/main/DeepSeek-R1-Distill-Qwen-32B.i1-Q4_0.gguf) | i1-Q4_0 | 18.8 | fast, low quality |
48
  | [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-Distill-Qwen-32B-i1-GGUF/resolve/main/DeepSeek-R1-Distill-Qwen-32B.i1-Q4_K_S.gguf) | i1-Q4_K_S | 18.9 | optimal size/speed/quality |
49
  | [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-Distill-Qwen-32B-i1-GGUF/resolve/main/DeepSeek-R1-Distill-Qwen-32B.i1-Q4_K_M.gguf) | i1-Q4_K_M | 20.0 | fast, recommended |
50
+ | [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-Distill-Qwen-32B-i1-GGUF/resolve/main/DeepSeek-R1-Distill-Qwen-32B.i1-Q4_1.gguf) | i1-Q4_1 | 20.7 | |
51
+ | [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-Distill-Qwen-32B-i1-GGUF/resolve/main/DeepSeek-R1-Distill-Qwen-32B.i1-Q5_K_S.gguf) | i1-Q5_K_S | 22.7 | |
52
+ | [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-Distill-Qwen-32B-i1-GGUF/resolve/main/DeepSeek-R1-Distill-Qwen-32B.i1-Q5_K_M.gguf) | i1-Q5_K_M | 23.4 | |
53
  | [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-Distill-Qwen-32B-i1-GGUF/resolve/main/DeepSeek-R1-Distill-Qwen-32B.i1-Q6_K.gguf) | i1-Q6_K | 27.0 | practically like static Q6_K |
54
 
55
  Here is a handy graph by ikawrakow comparing some lower-quality quant