community-verified · measured pool data

Can the GTX 1080 Ti 11GB run Qwen3.6-35B-A3B?

Yes — community-measured at 21.6 tok/s (5 runs at 2-bit).

Verified single-stream runs on the GTX 1080 Ti 11GB 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
2-bit 21.6 10.4 GB 8,192 llama.cpp
4-bit 10.3 10.2 GB 8,192 llama.cpp
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 →