mradermacher commited on
Commit
b366085
·
verified ·
1 Parent(s): 592fc23

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +8 -0
README.md CHANGED
@@ -46,19 +46,27 @@ more details, including on how to concatenate multi-part files.
46
  |:-----|:-----|--------:|:------|
47
  | [GGUF](https://huggingface.co/mradermacher/gpt-oss-20b-gemini-2.5-pro-distill-i1-GGUF/resolve/main/gpt-oss-20b-gemini-2.5-pro-distill.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own qwuants) |
48
  | [GGUF](https://huggingface.co/mradermacher/gpt-oss-20b-gemini-2.5-pro-distill-i1-GGUF/resolve/main/gpt-oss-20b-gemini-2.5-pro-distill.i1-IQ1_M.gguf) | i1-IQ1_M | 12.1 | mostly desperate |
 
49
  | [GGUF](https://huggingface.co/mradermacher/gpt-oss-20b-gemini-2.5-pro-distill-i1-GGUF/resolve/main/gpt-oss-20b-gemini-2.5-pro-distill.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 12.1 | |
50
  | [GGUF](https://huggingface.co/mradermacher/gpt-oss-20b-gemini-2.5-pro-distill-i1-GGUF/resolve/main/gpt-oss-20b-gemini-2.5-pro-distill.i1-IQ2_XS.gguf) | i1-IQ2_XS | 12.1 | |
51
  | [GGUF](https://huggingface.co/mradermacher/gpt-oss-20b-gemini-2.5-pro-distill-i1-GGUF/resolve/main/gpt-oss-20b-gemini-2.5-pro-distill.i1-Q3_K_S.gguf) | i1-Q3_K_S | 12.2 | IQ3_XS probably better |
52
  | [GGUF](https://huggingface.co/mradermacher/gpt-oss-20b-gemini-2.5-pro-distill-i1-GGUF/resolve/main/gpt-oss-20b-gemini-2.5-pro-distill.i1-IQ2_M.gguf) | i1-IQ2_M | 12.2 | |
 
 
 
53
  | [GGUF](https://huggingface.co/mradermacher/gpt-oss-20b-gemini-2.5-pro-distill-i1-GGUF/resolve/main/gpt-oss-20b-gemini-2.5-pro-distill.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 12.2 | lower quality |
54
  | [GGUF](https://huggingface.co/mradermacher/gpt-oss-20b-gemini-2.5-pro-distill-i1-GGUF/resolve/main/gpt-oss-20b-gemini-2.5-pro-distill.i1-Q2_K.gguf) | i1-Q2_K | 12.2 | IQ3_XXS probably better |
55
  | [GGUF](https://huggingface.co/mradermacher/gpt-oss-20b-gemini-2.5-pro-distill-i1-GGUF/resolve/main/gpt-oss-20b-gemini-2.5-pro-distill.i1-IQ4_XS.gguf) | i1-IQ4_XS | 12.2 | |
56
  | [GGUF](https://huggingface.co/mradermacher/gpt-oss-20b-gemini-2.5-pro-distill-i1-GGUF/resolve/main/gpt-oss-20b-gemini-2.5-pro-distill.i1-Q2_K_S.gguf) | i1-Q2_K_S | 12.2 | very low quality |
 
57
  | [GGUF](https://huggingface.co/mradermacher/gpt-oss-20b-gemini-2.5-pro-distill-i1-GGUF/resolve/main/gpt-oss-20b-gemini-2.5-pro-distill.i1-IQ3_M.gguf) | i1-IQ3_M | 12.3 | |
58
  | [GGUF](https://huggingface.co/mradermacher/gpt-oss-20b-gemini-2.5-pro-distill-i1-GGUF/resolve/main/gpt-oss-20b-gemini-2.5-pro-distill.i1-Q3_K_M.gguf) | i1-Q3_K_M | 13.0 | IQ3_S probably better |
59
  | [GGUF](https://huggingface.co/mradermacher/gpt-oss-20b-gemini-2.5-pro-distill-i1-GGUF/resolve/main/gpt-oss-20b-gemini-2.5-pro-distill.i1-Q3_K_L.gguf) | i1-Q3_K_L | 13.4 | IQ3_M probably better |
 
60
  | [GGUF](https://huggingface.co/mradermacher/gpt-oss-20b-gemini-2.5-pro-distill-i1-GGUF/resolve/main/gpt-oss-20b-gemini-2.5-pro-distill.i1-Q4_K_S.gguf) | i1-Q4_K_S | 14.8 | optimal size/speed/quality |
61
  | [GGUF](https://huggingface.co/mradermacher/gpt-oss-20b-gemini-2.5-pro-distill-i1-GGUF/resolve/main/gpt-oss-20b-gemini-2.5-pro-distill.i1-Q4_K_M.gguf) | i1-Q4_K_M | 15.9 | fast, recommended |
 
 
62
  | [GGUF](https://huggingface.co/mradermacher/gpt-oss-20b-gemini-2.5-pro-distill-i1-GGUF/resolve/main/gpt-oss-20b-gemini-2.5-pro-distill.i1-Q6_K.gguf) | i1-Q6_K | 22.3 | practically like static Q6_K |
63
 
64
  Here is a handy graph by ikawrakow comparing some lower-quality quant
 
46
  |:-----|:-----|--------:|:------|
47
  | [GGUF](https://huggingface.co/mradermacher/gpt-oss-20b-gemini-2.5-pro-distill-i1-GGUF/resolve/main/gpt-oss-20b-gemini-2.5-pro-distill.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own qwuants) |
48
  | [GGUF](https://huggingface.co/mradermacher/gpt-oss-20b-gemini-2.5-pro-distill-i1-GGUF/resolve/main/gpt-oss-20b-gemini-2.5-pro-distill.i1-IQ1_M.gguf) | i1-IQ1_M | 12.1 | mostly desperate |
49
+ | [GGUF](https://huggingface.co/mradermacher/gpt-oss-20b-gemini-2.5-pro-distill-i1-GGUF/resolve/main/gpt-oss-20b-gemini-2.5-pro-distill.i1-IQ1_S.gguf) | i1-IQ1_S | 12.1 | for the desperate |
50
  | [GGUF](https://huggingface.co/mradermacher/gpt-oss-20b-gemini-2.5-pro-distill-i1-GGUF/resolve/main/gpt-oss-20b-gemini-2.5-pro-distill.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 12.1 | |
51
  | [GGUF](https://huggingface.co/mradermacher/gpt-oss-20b-gemini-2.5-pro-distill-i1-GGUF/resolve/main/gpt-oss-20b-gemini-2.5-pro-distill.i1-IQ2_XS.gguf) | i1-IQ2_XS | 12.1 | |
52
  | [GGUF](https://huggingface.co/mradermacher/gpt-oss-20b-gemini-2.5-pro-distill-i1-GGUF/resolve/main/gpt-oss-20b-gemini-2.5-pro-distill.i1-Q3_K_S.gguf) | i1-Q3_K_S | 12.2 | IQ3_XS probably better |
53
  | [GGUF](https://huggingface.co/mradermacher/gpt-oss-20b-gemini-2.5-pro-distill-i1-GGUF/resolve/main/gpt-oss-20b-gemini-2.5-pro-distill.i1-IQ2_M.gguf) | i1-IQ2_M | 12.2 | |
54
+ | [GGUF](https://huggingface.co/mradermacher/gpt-oss-20b-gemini-2.5-pro-distill-i1-GGUF/resolve/main/gpt-oss-20b-gemini-2.5-pro-distill.i1-IQ2_S.gguf) | i1-IQ2_S | 12.2 | |
55
+ | [GGUF](https://huggingface.co/mradermacher/gpt-oss-20b-gemini-2.5-pro-distill-i1-GGUF/resolve/main/gpt-oss-20b-gemini-2.5-pro-distill.i1-IQ3_S.gguf) | i1-IQ3_S | 12.2 | beats Q3_K* |
56
+ | [GGUF](https://huggingface.co/mradermacher/gpt-oss-20b-gemini-2.5-pro-distill-i1-GGUF/resolve/main/gpt-oss-20b-gemini-2.5-pro-distill.i1-IQ3_XS.gguf) | i1-IQ3_XS | 12.2 | |
57
  | [GGUF](https://huggingface.co/mradermacher/gpt-oss-20b-gemini-2.5-pro-distill-i1-GGUF/resolve/main/gpt-oss-20b-gemini-2.5-pro-distill.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 12.2 | lower quality |
58
  | [GGUF](https://huggingface.co/mradermacher/gpt-oss-20b-gemini-2.5-pro-distill-i1-GGUF/resolve/main/gpt-oss-20b-gemini-2.5-pro-distill.i1-Q2_K.gguf) | i1-Q2_K | 12.2 | IQ3_XXS probably better |
59
  | [GGUF](https://huggingface.co/mradermacher/gpt-oss-20b-gemini-2.5-pro-distill-i1-GGUF/resolve/main/gpt-oss-20b-gemini-2.5-pro-distill.i1-IQ4_XS.gguf) | i1-IQ4_XS | 12.2 | |
60
  | [GGUF](https://huggingface.co/mradermacher/gpt-oss-20b-gemini-2.5-pro-distill-i1-GGUF/resolve/main/gpt-oss-20b-gemini-2.5-pro-distill.i1-Q2_K_S.gguf) | i1-Q2_K_S | 12.2 | very low quality |
61
+ | [GGUF](https://huggingface.co/mradermacher/gpt-oss-20b-gemini-2.5-pro-distill-i1-GGUF/resolve/main/gpt-oss-20b-gemini-2.5-pro-distill.i1-Q4_0.gguf) | i1-Q4_0 | 12.2 | fast, low quality |
62
  | [GGUF](https://huggingface.co/mradermacher/gpt-oss-20b-gemini-2.5-pro-distill-i1-GGUF/resolve/main/gpt-oss-20b-gemini-2.5-pro-distill.i1-IQ3_M.gguf) | i1-IQ3_M | 12.3 | |
63
  | [GGUF](https://huggingface.co/mradermacher/gpt-oss-20b-gemini-2.5-pro-distill-i1-GGUF/resolve/main/gpt-oss-20b-gemini-2.5-pro-distill.i1-Q3_K_M.gguf) | i1-Q3_K_M | 13.0 | IQ3_S probably better |
64
  | [GGUF](https://huggingface.co/mradermacher/gpt-oss-20b-gemini-2.5-pro-distill-i1-GGUF/resolve/main/gpt-oss-20b-gemini-2.5-pro-distill.i1-Q3_K_L.gguf) | i1-Q3_K_L | 13.4 | IQ3_M probably better |
65
+ | [GGUF](https://huggingface.co/mradermacher/gpt-oss-20b-gemini-2.5-pro-distill-i1-GGUF/resolve/main/gpt-oss-20b-gemini-2.5-pro-distill.i1-Q4_1.gguf) | i1-Q4_1 | 13.5 | |
66
  | [GGUF](https://huggingface.co/mradermacher/gpt-oss-20b-gemini-2.5-pro-distill-i1-GGUF/resolve/main/gpt-oss-20b-gemini-2.5-pro-distill.i1-Q4_K_S.gguf) | i1-Q4_K_S | 14.8 | optimal size/speed/quality |
67
  | [GGUF](https://huggingface.co/mradermacher/gpt-oss-20b-gemini-2.5-pro-distill-i1-GGUF/resolve/main/gpt-oss-20b-gemini-2.5-pro-distill.i1-Q4_K_M.gguf) | i1-Q4_K_M | 15.9 | fast, recommended |
68
+ | [GGUF](https://huggingface.co/mradermacher/gpt-oss-20b-gemini-2.5-pro-distill-i1-GGUF/resolve/main/gpt-oss-20b-gemini-2.5-pro-distill.i1-Q5_K_S.gguf) | i1-Q5_K_S | 16.0 | |
69
+ | [GGUF](https://huggingface.co/mradermacher/gpt-oss-20b-gemini-2.5-pro-distill-i1-GGUF/resolve/main/gpt-oss-20b-gemini-2.5-pro-distill.i1-Q5_K_M.gguf) | i1-Q5_K_M | 17.0 | |
70
  | [GGUF](https://huggingface.co/mradermacher/gpt-oss-20b-gemini-2.5-pro-distill-i1-GGUF/resolve/main/gpt-oss-20b-gemini-2.5-pro-distill.i1-Q6_K.gguf) | i1-Q6_K | 22.3 | practically like static Q6_K |
71
 
72
  Here is a handy graph by ikawrakow comparing some lower-quality quant