Qwen3-30B-A3B FP8-OC
Derived from Qwen/Qwen3-30B-A3B at revision ad44e777bcd18fa416d9da3bd8f70d33ebb85d39.
LLM Compressor quantizes attention and expert matrix weights to E4M3FN with one FP32 scale per output channel. HART stores those FP8 bytes and scales in the Bertha EVT0 packed weight format. Other model parameters remain BF16. This checkpoint requires the HyperAccel vLLM plugin.
- Downloads last month
- 54
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support