Update README.md
Browse files
README.md
CHANGED
|
@@ -94,6 +94,7 @@ python -m mlx_lm convert \
|
|
| 94 |
- Some non-expert tensors (embeddings, norms, router) remain FP16.
|
| 95 |
|
| 96 |
## Sibling & reference models
|
|
|
|
| 97 |
- halley-ai/gpt-oss-20b-MLX-4bit-gs32
|
| 98 |
- Reference (8-bit, upstream): lmstudio-community/gpt-oss-20b-MLX-8bit
|
| 99 |
|
|
|
|
| 94 |
- Some non-expert tensors (embeddings, norms, router) remain FP16.
|
| 95 |
|
| 96 |
## Sibling & reference models
|
| 97 |
+
- halley-ai/gpt-oss-20b-MLX-5bit-gs32
|
| 98 |
- halley-ai/gpt-oss-20b-MLX-4bit-gs32
|
| 99 |
- Reference (8-bit, upstream): lmstudio-community/gpt-oss-20b-MLX-8bit
|
| 100 |
|