Update README.md
Browse files
README.md
CHANGED
|
@@ -14,6 +14,15 @@ tags:
|
|
| 14 |
- mxfp4_hybrid
|
| 15 |
---
|
| 16 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 17 |
# Unsloth - Qwen3 VL 8B Instruct MXFP4 Hybrid GGUF
|
| 18 |
|
| 19 |
**Dense model utilizing MXFP4_MOE with hybrid weights on a dense model. Achieving interesting results that show smaller file size, more TPS, and near lossless precision.**
|
|
|
|
| 14 |
- mxfp4_hybrid
|
| 15 |
---
|
| 16 |
|
| 17 |
+
# DEPRECIATED!
|
| 18 |
+
|
| 19 |
+
This model was surpassed by the new MagicQuant hybrids. The collection can be found here:
|
| 20 |
+
|
| 21 |
+
https://huggingface.co/collections/magiccodingman/magic-quant
|
| 22 |
+
|
| 23 |
+
Use the new version. This shown MXFP4 hybrid is no longer viable in comparison, nor really useable. The data collected is good for understanding and research, but it's not as good for real use.
|
| 24 |
+
|
| 25 |
+
|
| 26 |
# Unsloth - Qwen3 VL 8B Instruct MXFP4 Hybrid GGUF
|
| 27 |
|
| 28 |
**Dense model utilizing MXFP4_MOE with hybrid weights on a dense model. Achieving interesting results that show smaller file size, more TPS, and near lossless precision.**
|