Hyper-AI/Qwen3-VL-2B-Instruct-fp8
Image-Text-to-Text • Updated • 55 • 1
qwen3-vl-fp8
fp8 quant for qwen3-vl models, nearly half memory decrease, speedup 30%, vllm serve can run
fp8 quant for qwen3-vl models, nearly half memory decrease, speedup 30%, vllm serve can run