Qwen/Qwen3-0.6B-FP8

Quantization vs Qwen/Qwen3-0.6B. Qwen/Qwen3-0.6B-FP8 is a quantized version of the other (BF16/F8_E4M3).

1 derivatives checked

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

On the Hub · Downloads on Model Pulse