community-verified · measured pool data

Can the RTX 3080 12GB run Qwen2.5-Coder-7B-Instruct?

Yes — community-measured at 140.8 tok/s (3 runs at 4-bit).

Verified single-stream runs on the RTX 3080 12GB 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 140.8 8.2 GB 2,048 llama.cpp, ollama
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 →