Qwen
Collection
Models from the Qwen team
•
13 items
•
Updated
•
1
This is a MXFP4_MOE quantization of the model Qwen3-Coder-REAP-246B-A35B
Original model: https://huggingface.co/cerebras/Qwen3-Coder-REAP-246B-A35B-FP8
The model was originally in FP8, which limits its precision.
I attempted to apply MXFP4 quantization after converting the model to FP32, but the quality degradation from the initial FP8 quantization cannot be fully reversed.
- Downloads last month
- 242
Hardware compatibility
Log In
to view the estimation
4-bit
Model tree for noctrex/Qwen3-Coder-REAP-246B-A35B-MXFP4_MOE-GGUF
Base model
Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8
Quantized
cerebras/Qwen3-Coder-REAP-246B-A35B-FP8