Qwen/Qwen3-VL-2B-Instruct-FP8

Quantization vs Qwen/Qwen3-VL-2B-Instruct. Qwen/Qwen3-VL-2B-Instruct-FP8 is a quantized version of the other (BF16/F8_E4M3).

1 derivatives checked

• unsloth/Qwen3-VL-2B-Instruct-FP8: Identical copy

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

On the Hub · Downloads on Model Pulse