et0dev
/

Qwen3.5-122B-A10B-NVFP4-Full-GB10

Image-Text-to-Text

compressed-tensors

Mixture of Experts

8-bit precision

Model card Files Files and versions

Qwen3.5-122B-A10B-NVFP4-Full-GB10 / config.json

Commit History

Add ParallelLMHead to quantization targets for vLLM compat

02083ec
verified

demon-zombie commited on May 17

NVFP4-only quant v2 (all Linear incl MTP → NVFP4)

496733f
verified

demon-zombie commited on May 17