nm-testing/Qwen2.5-Coder-32B-Instruct-FP8-dynamic

Quantization vs Qwen/Qwen2.5-Coder-32B-Instruct. nm-testing/Qwen2.5-Coder-32B-Instruct-FP8-dynamic is a quantized version of the other (F8_E4M3/BF16).

5 other repos hold byte-for-byte identical weight files.

On the Hub · Downloads on Model Pulse