dudeman2512/Qwen3.8-2.4T-A95B-FP8

Quantization vs Qwen/Qwen3.8-2.4T-A95B. dudeman2512/Qwen3.8-2.4T-A95B-FP8 is a quantized version of the other (F8_E4M3/BF16).

On the Hub · Downloads on Model Pulse