Models / Qwen3 8B

Best home rig for Qwen3 8B

Quick answer

What is the fastest measured hardware for Qwen3 8B?
Apple M3 Pro (18 GB): Llama 3.1 8B at 27.2 tok/s, Qwen3 14B at 14.5 (Ollama, median of 6 runs): 25.3 tok/s generation (Ollama 0.40.13 (Metal), Q4_K_M (5.23 GB, Ollama tag qwen3:8b)), from https://localaimaster.com/benchmarks.

Last updated: 4 Nov 2026

Legacy model1 measured resultfastest plain decode: 25.3 tok/s

Older model. For current picks see current models.

Real, measured generation speeds for Qwen3 8B on home hardware, fastest first. Different quants/engines aren't directly comparable.

Build	Quant	Engine	tok/s	Prompt processing (tok/s)	Cost	Source
Apple M3 Pro (18 GB): Llama 3.1 8B at 27.2 tok/s, Qwen3 14B at 14.5 (Ollama, median of 6 runs)	Q4_K_M (5.23 GB, Ollama tag qwen3:8b)	Ollama 0.40.13 (Metal)	25.3	–		localaimaster.com ↗

Prompt processing = prefill speed reported by the source, @ prompt length. * est. TTFT @8k is calculated from measured prefill, not measured. Why it matters.

Rent before you buy: try this model on a cloud GPU for a few dollars first: Runpod (referral link; sign up with Google to get the new-user bonus)

FAQ

What is the fastest measured hardware for Qwen3 8B?

Apple M3 Pro (18 GB): Llama 3.1 8B at 27.2 tok/s, Qwen3 14B at 14.5 (Ollama, median of 6 runs): 25.3 tok/s generation (Ollama 0.40.13 (Metal), Q4_K_M (5.23 GB, Ollama tag qwen3:8b)), from https://localaimaster.com/benchmarks.