community-verified · measured pool data

Can the GB10 Grace Blackwell 128GB run Qwen3.6-27B-AEON-Ultimate-Uncensored-Multimodal-NVFP4-MTP-XS?

Yes — community-measured at 29.8 tok/s (7 runs at 4-bit).

Verified single-stream runs on the GB10 Grace Blackwell 128GB from the localmaxxing public pool. Every number on this page is measured — nothing here is estimated.

Quantization Median tok/s TTFT (ms) Peak VRAM Max context tested Engines
4-bit 29.8 737.5 86.1 GB 262,144 vllm
Go deeper
I have a goal — find models that fit my use case → I have hardware — browse everything my rig can run → All machine × model answer pages →