auto-patch README.md
Browse files
README.md
CHANGED
|
@@ -40,6 +40,11 @@ more details, including on how to concatenate multi-part files.
|
|
| 40 |
| Link | Type | Size/GB | Notes |
|
| 41 |
|:-----|:-----|--------:|:------|
|
| 42 |
| [GGUF](https://huggingface.co/mradermacher/ThinMQM-32B-i1-GGUF/resolve/main/ThinMQM-32B.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own qwuants) |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 43 |
|
| 44 |
Here is a handy graph by ikawrakow comparing some lower-quality quant
|
| 45 |
types (lower is better):
|
|
|
|
| 40 |
| Link | Type | Size/GB | Notes |
|
| 41 |
|:-----|:-----|--------:|:------|
|
| 42 |
| [GGUF](https://huggingface.co/mradermacher/ThinMQM-32B-i1-GGUF/resolve/main/ThinMQM-32B.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own qwuants) |
|
| 43 |
+
| [GGUF](https://huggingface.co/mradermacher/ThinMQM-32B-i1-GGUF/resolve/main/ThinMQM-32B.i1-Q2_K.gguf) | i1-Q2_K | 12.4 | IQ3_XXS probably better |
|
| 44 |
+
| [GGUF](https://huggingface.co/mradermacher/ThinMQM-32B-i1-GGUF/resolve/main/ThinMQM-32B.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 12.9 | lower quality |
|
| 45 |
+
| [GGUF](https://huggingface.co/mradermacher/ThinMQM-32B-i1-GGUF/resolve/main/ThinMQM-32B.i1-IQ3_M.gguf) | i1-IQ3_M | 14.9 | |
|
| 46 |
+
| [GGUF](https://huggingface.co/mradermacher/ThinMQM-32B-i1-GGUF/resolve/main/ThinMQM-32B.i1-Q3_K_M.gguf) | i1-Q3_K_M | 16.0 | IQ3_S probably better |
|
| 47 |
+
| [GGUF](https://huggingface.co/mradermacher/ThinMQM-32B-i1-GGUF/resolve/main/ThinMQM-32B.i1-Q4_K_S.gguf) | i1-Q4_K_S | 18.9 | optimal size/speed/quality |
|
| 48 |
|
| 49 |
Here is a handy graph by ikawrakow comparing some lower-quality quant
|
| 50 |
types (lower is better):
|