auto-patch README.md
Browse files
README.md
CHANGED
@@ -52,14 +52,19 @@ more details, including on how to concatenate multi-part files.
|
|
52 |
| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-The-Wisemen-QwQ-Deep-Tiny-Sherlock-32B-i1-GGUF/resolve/main/Qwen2.5-The-Wisemen-QwQ-Deep-Tiny-Sherlock-32B.i1-Q2_K_S.gguf) | i1-Q2_K_S | 11.6 | very low quality |
|
53 |
| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-The-Wisemen-QwQ-Deep-Tiny-Sherlock-32B-i1-GGUF/resolve/main/Qwen2.5-The-Wisemen-QwQ-Deep-Tiny-Sherlock-32B.i1-Q2_K.gguf) | i1-Q2_K | 12.4 | IQ3_XXS probably better |
|
54 |
| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-The-Wisemen-QwQ-Deep-Tiny-Sherlock-32B-i1-GGUF/resolve/main/Qwen2.5-The-Wisemen-QwQ-Deep-Tiny-Sherlock-32B.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 12.9 | lower quality |
|
|
|
55 |
| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-The-Wisemen-QwQ-Deep-Tiny-Sherlock-32B-i1-GGUF/resolve/main/Qwen2.5-The-Wisemen-QwQ-Deep-Tiny-Sherlock-32B.i1-Q3_K_S.gguf) | i1-Q3_K_S | 14.5 | IQ3_XS probably better |
|
|
|
56 |
| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-The-Wisemen-QwQ-Deep-Tiny-Sherlock-32B-i1-GGUF/resolve/main/Qwen2.5-The-Wisemen-QwQ-Deep-Tiny-Sherlock-32B.i1-IQ3_M.gguf) | i1-IQ3_M | 14.9 | |
|
57 |
| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-The-Wisemen-QwQ-Deep-Tiny-Sherlock-32B-i1-GGUF/resolve/main/Qwen2.5-The-Wisemen-QwQ-Deep-Tiny-Sherlock-32B.i1-Q3_K_M.gguf) | i1-Q3_K_M | 16.0 | IQ3_S probably better |
|
58 |
| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-The-Wisemen-QwQ-Deep-Tiny-Sherlock-32B-i1-GGUF/resolve/main/Qwen2.5-The-Wisemen-QwQ-Deep-Tiny-Sherlock-32B.i1-Q3_K_L.gguf) | i1-Q3_K_L | 17.3 | IQ3_M probably better |
|
59 |
| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-The-Wisemen-QwQ-Deep-Tiny-Sherlock-32B-i1-GGUF/resolve/main/Qwen2.5-The-Wisemen-QwQ-Deep-Tiny-Sherlock-32B.i1-IQ4_XS.gguf) | i1-IQ4_XS | 17.8 | |
|
|
|
60 |
| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-The-Wisemen-QwQ-Deep-Tiny-Sherlock-32B-i1-GGUF/resolve/main/Qwen2.5-The-Wisemen-QwQ-Deep-Tiny-Sherlock-32B.i1-Q4_K_S.gguf) | i1-Q4_K_S | 18.9 | optimal size/speed/quality |
|
61 |
| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-The-Wisemen-QwQ-Deep-Tiny-Sherlock-32B-i1-GGUF/resolve/main/Qwen2.5-The-Wisemen-QwQ-Deep-Tiny-Sherlock-32B.i1-Q4_K_M.gguf) | i1-Q4_K_M | 19.9 | fast, recommended |
|
|
|
62 |
| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-The-Wisemen-QwQ-Deep-Tiny-Sherlock-32B-i1-GGUF/resolve/main/Qwen2.5-The-Wisemen-QwQ-Deep-Tiny-Sherlock-32B.i1-Q5_K_S.gguf) | i1-Q5_K_S | 22.7 | |
|
|
|
63 |
| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-The-Wisemen-QwQ-Deep-Tiny-Sherlock-32B-i1-GGUF/resolve/main/Qwen2.5-The-Wisemen-QwQ-Deep-Tiny-Sherlock-32B.i1-Q6_K.gguf) | i1-Q6_K | 27.0 | practically like static Q6_K |
|
64 |
|
65 |
Here is a handy graph by ikawrakow comparing some lower-quality quant
|
|
|
52 |
| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-The-Wisemen-QwQ-Deep-Tiny-Sherlock-32B-i1-GGUF/resolve/main/Qwen2.5-The-Wisemen-QwQ-Deep-Tiny-Sherlock-32B.i1-Q2_K_S.gguf) | i1-Q2_K_S | 11.6 | very low quality |
|
53 |
| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-The-Wisemen-QwQ-Deep-Tiny-Sherlock-32B-i1-GGUF/resolve/main/Qwen2.5-The-Wisemen-QwQ-Deep-Tiny-Sherlock-32B.i1-Q2_K.gguf) | i1-Q2_K | 12.4 | IQ3_XXS probably better |
|
54 |
| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-The-Wisemen-QwQ-Deep-Tiny-Sherlock-32B-i1-GGUF/resolve/main/Qwen2.5-The-Wisemen-QwQ-Deep-Tiny-Sherlock-32B.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 12.9 | lower quality |
|
55 |
+
| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-The-Wisemen-QwQ-Deep-Tiny-Sherlock-32B-i1-GGUF/resolve/main/Qwen2.5-The-Wisemen-QwQ-Deep-Tiny-Sherlock-32B.i1-IQ3_XS.gguf) | i1-IQ3_XS | 13.8 | |
|
56 |
| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-The-Wisemen-QwQ-Deep-Tiny-Sherlock-32B-i1-GGUF/resolve/main/Qwen2.5-The-Wisemen-QwQ-Deep-Tiny-Sherlock-32B.i1-Q3_K_S.gguf) | i1-Q3_K_S | 14.5 | IQ3_XS probably better |
|
57 |
+
| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-The-Wisemen-QwQ-Deep-Tiny-Sherlock-32B-i1-GGUF/resolve/main/Qwen2.5-The-Wisemen-QwQ-Deep-Tiny-Sherlock-32B.i1-IQ3_S.gguf) | i1-IQ3_S | 14.5 | beats Q3_K* |
|
58 |
| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-The-Wisemen-QwQ-Deep-Tiny-Sherlock-32B-i1-GGUF/resolve/main/Qwen2.5-The-Wisemen-QwQ-Deep-Tiny-Sherlock-32B.i1-IQ3_M.gguf) | i1-IQ3_M | 14.9 | |
|
59 |
| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-The-Wisemen-QwQ-Deep-Tiny-Sherlock-32B-i1-GGUF/resolve/main/Qwen2.5-The-Wisemen-QwQ-Deep-Tiny-Sherlock-32B.i1-Q3_K_M.gguf) | i1-Q3_K_M | 16.0 | IQ3_S probably better |
|
60 |
| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-The-Wisemen-QwQ-Deep-Tiny-Sherlock-32B-i1-GGUF/resolve/main/Qwen2.5-The-Wisemen-QwQ-Deep-Tiny-Sherlock-32B.i1-Q3_K_L.gguf) | i1-Q3_K_L | 17.3 | IQ3_M probably better |
|
61 |
| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-The-Wisemen-QwQ-Deep-Tiny-Sherlock-32B-i1-GGUF/resolve/main/Qwen2.5-The-Wisemen-QwQ-Deep-Tiny-Sherlock-32B.i1-IQ4_XS.gguf) | i1-IQ4_XS | 17.8 | |
|
62 |
+
| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-The-Wisemen-QwQ-Deep-Tiny-Sherlock-32B-i1-GGUF/resolve/main/Qwen2.5-The-Wisemen-QwQ-Deep-Tiny-Sherlock-32B.i1-Q4_0.gguf) | i1-Q4_0 | 18.8 | fast, low quality |
|
63 |
| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-The-Wisemen-QwQ-Deep-Tiny-Sherlock-32B-i1-GGUF/resolve/main/Qwen2.5-The-Wisemen-QwQ-Deep-Tiny-Sherlock-32B.i1-Q4_K_S.gguf) | i1-Q4_K_S | 18.9 | optimal size/speed/quality |
|
64 |
| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-The-Wisemen-QwQ-Deep-Tiny-Sherlock-32B-i1-GGUF/resolve/main/Qwen2.5-The-Wisemen-QwQ-Deep-Tiny-Sherlock-32B.i1-Q4_K_M.gguf) | i1-Q4_K_M | 19.9 | fast, recommended |
|
65 |
+
| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-The-Wisemen-QwQ-Deep-Tiny-Sherlock-32B-i1-GGUF/resolve/main/Qwen2.5-The-Wisemen-QwQ-Deep-Tiny-Sherlock-32B.i1-Q4_1.gguf) | i1-Q4_1 | 20.7 | |
|
66 |
| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-The-Wisemen-QwQ-Deep-Tiny-Sherlock-32B-i1-GGUF/resolve/main/Qwen2.5-The-Wisemen-QwQ-Deep-Tiny-Sherlock-32B.i1-Q5_K_S.gguf) | i1-Q5_K_S | 22.7 | |
|
67 |
+
| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-The-Wisemen-QwQ-Deep-Tiny-Sherlock-32B-i1-GGUF/resolve/main/Qwen2.5-The-Wisemen-QwQ-Deep-Tiny-Sherlock-32B.i1-Q5_K_M.gguf) | i1-Q5_K_M | 23.4 | |
|
68 |
| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-The-Wisemen-QwQ-Deep-Tiny-Sherlock-32B-i1-GGUF/resolve/main/Qwen2.5-The-Wisemen-QwQ-Deep-Tiny-Sherlock-32B.i1-Q6_K.gguf) | i1-Q6_K | 27.0 | practically like static Q6_K |
|
69 |
|
70 |
Here is a handy graph by ikawrakow comparing some lower-quality quant
|