can-i-run-this-llm

Can I run this LLM?

Can a NVIDIA RTX 5070 (12GB) run Qwen3 8B?

Qwen · Apache 2.0 · estimated for a 12.0 GB machine at 4K context.

Yes — it runs great.

Best fit: Qwen3 8B at Q6_K · 6.7 GB · 57–86 tok/s on a NVIDIA RTX 5070 (12GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K3.3 GB95–142 tok/sRuns great
Q3_K_M4.1 GB82–122 tok/sRuns great
Q4_K_M5.0 GB71–107 tok/sRuns great
Q5_K_M5.9 GB64–95 tok/sRuns great
Q6_K6.7 GB57–86 tok/sRuns great
Q8_08.7 GB47–70 tok/sTight / slow
FP1616.4 GB27–41 tok/sWon't fit

Ran Qwen3 8B on a NVIDIA RTX 5070 (12GB)? Add your real numbers →