Qwen/Qwen3-4B-Instruct-2507-FP8

Quantization vs Qwen/Qwen3-4B-Instruct-2507. Qwen/Qwen3-4B-Instruct-2507-FP8 is a quantized version of the other (F8_E4M3/F16).

1 derivatives checked

• unsloth/Qwen3-4B-Instruct-2507-FP8: Same weights, converted

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

On the Hub · Downloads on Model Pulse