auto-patch README.md
Browse files
README.md
CHANGED
|
@@ -37,7 +37,19 @@ more details, including on how to concatenate multi-part files.
|
|
| 37 |
| Link | Type | Size/GB | Notes |
|
| 38 |
|:-----|:-----|--------:|:------|
|
| 39 |
| [GGUF](https://huggingface.co/mradermacher/GeometryReasoning-GGUF/resolve/main/GeometryReasoning.mmproj-Q8_0.gguf) | mmproj-Q8_0 | 0.9 | multi-modal supplement |
|
|
|
|
| 40 |
| [GGUF](https://huggingface.co/mradermacher/GeometryReasoning-GGUF/resolve/main/GeometryReasoning.mmproj-f16.gguf) | mmproj-f16 | 1.4 | multi-modal supplement |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 41 |
|
| 42 |
Here is a handy graph by ikawrakow comparing some lower-quality quant
|
| 43 |
types (lower is better):
|
|
|
|
| 37 |
| Link | Type | Size/GB | Notes |
|
| 38 |
|:-----|:-----|--------:|:------|
|
| 39 |
| [GGUF](https://huggingface.co/mradermacher/GeometryReasoning-GGUF/resolve/main/GeometryReasoning.mmproj-Q8_0.gguf) | mmproj-Q8_0 | 0.9 | multi-modal supplement |
|
| 40 |
+
| [GGUF](https://huggingface.co/mradermacher/GeometryReasoning-GGUF/resolve/main/GeometryReasoning.Q2_K.gguf) | Q2_K | 1.4 | |
|
| 41 |
| [GGUF](https://huggingface.co/mradermacher/GeometryReasoning-GGUF/resolve/main/GeometryReasoning.mmproj-f16.gguf) | mmproj-f16 | 1.4 | multi-modal supplement |
|
| 42 |
+
| [GGUF](https://huggingface.co/mradermacher/GeometryReasoning-GGUF/resolve/main/GeometryReasoning.Q3_K_S.gguf) | Q3_K_S | 1.6 | |
|
| 43 |
+
| [GGUF](https://huggingface.co/mradermacher/GeometryReasoning-GGUF/resolve/main/GeometryReasoning.Q3_K_M.gguf) | Q3_K_M | 1.7 | lower quality |
|
| 44 |
+
| [GGUF](https://huggingface.co/mradermacher/GeometryReasoning-GGUF/resolve/main/GeometryReasoning.Q3_K_L.gguf) | Q3_K_L | 1.8 | |
|
| 45 |
+
| [GGUF](https://huggingface.co/mradermacher/GeometryReasoning-GGUF/resolve/main/GeometryReasoning.IQ4_XS.gguf) | IQ4_XS | 1.9 | |
|
| 46 |
+
| [GGUF](https://huggingface.co/mradermacher/GeometryReasoning-GGUF/resolve/main/GeometryReasoning.Q4_K_S.gguf) | Q4_K_S | 1.9 | fast, recommended |
|
| 47 |
+
| [GGUF](https://huggingface.co/mradermacher/GeometryReasoning-GGUF/resolve/main/GeometryReasoning.Q4_K_M.gguf) | Q4_K_M | 2.0 | fast, recommended |
|
| 48 |
+
| [GGUF](https://huggingface.co/mradermacher/GeometryReasoning-GGUF/resolve/main/GeometryReasoning.Q5_K_S.gguf) | Q5_K_S | 2.3 | |
|
| 49 |
+
| [GGUF](https://huggingface.co/mradermacher/GeometryReasoning-GGUF/resolve/main/GeometryReasoning.Q5_K_M.gguf) | Q5_K_M | 2.3 | |
|
| 50 |
+
| [GGUF](https://huggingface.co/mradermacher/GeometryReasoning-GGUF/resolve/main/GeometryReasoning.Q6_K.gguf) | Q6_K | 2.6 | very good quality |
|
| 51 |
+
| [GGUF](https://huggingface.co/mradermacher/GeometryReasoning-GGUF/resolve/main/GeometryReasoning.Q8_0.gguf) | Q8_0 | 3.4 | fast, best quality |
|
| 52 |
+
| [GGUF](https://huggingface.co/mradermacher/GeometryReasoning-GGUF/resolve/main/GeometryReasoning.f16.gguf) | f16 | 6.3 | 16 bpw, overkill |
|
| 53 |
|
| 54 |
Here is a handy graph by ikawrakow comparing some lower-quality quant
|
| 55 |
types (lower is better):
|