tturing/Qwen3-Omni-30B-A3B-Thinking-FP8

Quantization vs Qwen/Qwen3-Omni-30B-A3B-Thinking. tturing/Qwen3-Omni-30B-A3B-Thinking-FP8 is a quantized version of the other (F8_E4M3/BF16).

On the Hub · Downloads on Model Pulse