Can 4x Apple M5 Ultra run Qwen3.8 27B?

Q: Can 4x Apple M5 Ultra run Qwen3.8 27B?

Yes. Measured 50.89 tok/s generation on 4x Apple M5 Ultra, via MLX, 4-node tensor parallel, BF16, 8,192-token context. Source: https://machinelearning.apple.com/research/mlx-distributed-inference

Yes. Measured 50.89 tok/s generation (MLX, 4-node tensor parallel, BF16, 8,192-token context; source).

Every measured result for Qwen3.8 27B on 4x Apple M5 Ultra

Build	Quant / setup	Engine	tok/s
4x Mac Studio M5 Ultra cluster (Thunderbolt 5 RDMA): Muse Spark Open at 36.7 tok/s	BF16, 8,192-token context	MLX, 4-node tensor parallel	50.89	source

Speeds are decode (generation) tokens/sec as reported by each source; quant, engine and context differ, so small gaps are noise.

All measured speeds for Qwen3.8 27B: best home rig for Qwen3.8 27B.

Qwen3.8 27B on other hardware: 2x Apple M5 Ultra · Apple M3 Ultra · Apple M5 Ultra · RTX 3060 12GB · RTX 3090 · RTX 4060 Ti 16GB · RTX Spark N1X

Other models measured on 4x Apple M5 Ultra: Mistral Medium 3.5 128B · Muse Spark Open 816B-A42B

Not enough VRAM? Rent before you buy. Run Qwen3.8 27B on a bigger GPU on a rented 24–96 GB cloud GPU by the hour and see the real speed before spending €1,000+. Try it on RunPod
Referral link: RigBase may earn RunPod credit if you sign up. It never affects our data.

SPONSOR
Your brand here. One sponsor slot on this page, shown to people choosing AI hardware. Sponsor RigBase →