magiccodingman commited on
Commit
cfcc333
·
verified ·
1 Parent(s): bd267e6

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +9 -0
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.**