community-verified · measured pool data

Can the Tesla V100 32GB ×2 run Qwen3-Coder-30B-A3B-Instruct?

Yes — community-measured at 100.5 tok/s (2 runs at 6-bit).

Verified single-stream runs on the Tesla V100 32GB ×2 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
6-bit	100.5	—	58 GB	65,536	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 →