Best home rig for Qwen3.8 27B

Will it fit my GPU? Best value GPU per euro →

Real, measured generation speeds for Qwen3.8 27B on home hardware, fastest first. Different quants/engines aren't directly comparable.

Build	Quant	Engine	tok/s
Single RTX 3090: Qwen3.8 27B at 78-140 tok/s with the OpenJet megakernel vs llama.cpp	Q4_K_M (unsloth), greedy code prompt	OpenJet megakernel (MTP, 4 drafts)	139.7	source
Single RTX 3090: Qwen3.8 27B at 78-140 tok/s with the OpenJet megakernel vs llama.cpp	Q4_K_M (unsloth), reasoning mode	OpenJet megakernel (MTP)	78.0	source
Single RTX 3090: Qwen3.8 27B at 78-140 tok/s with the OpenJet megakernel vs llama.cpp	Q4_K_M (unsloth), greedy code prompt	llama.cpp (MTP, 2 drafts)	72.5	source
Single RTX 3090: Qwen3.8 27B at 78-140 tok/s with the OpenJet megakernel vs llama.cpp	Q4_K_M (unsloth), reasoning mode	llama.cpp (MTP, 2 drafts)	50.9	source
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
Single RTX 3090: Qwen3.8 27B at 78-140 tok/s with the OpenJet megakernel vs llama.cpp	Q4_K_M (unsloth), no speculation	OpenJet megakernel	42.9	source
Single RTX 3090: Qwen3.8 27B at 78-140 tok/s with the OpenJet megakernel vs llama.cpp	Q4_K_M (unsloth), no speculation	llama.cpp	40.4	source
RTX 3090: 2026 models (llamabench community)	llama-bench tg128 (quant per result)	llama.cpp	38.2-71.6	source
2x Mac Studio M5 Ultra cluster (Thunderbolt 5 RDMA): Muse Spark Open 816B	BF16, 8,192-token context	MLX, 2-node tensor parallel	33.27	source
Mac Studio M5 Ultra 512GB: Qwen3.8 27B and Mistral Medium 3.5 (Apple MLX benchmark)	BF16, 8,192-token context	MLX (mlx_lm.benchmark)	19.69	source
Microsoft Surface Laptop Ultra (RTX Spark N1X): llama.cpp speeds on 2026 models (Micro Center)	general, short prompt	llama.cpp (Nvidia ARM64 build)	14.5	source
Mac Studio M3 Ultra 512GB: Qwen3.8 27B and Mistral Medium 3.5 (Apple MLX benchmark)	BF16, 8,192-token context	MLX (mlx_lm.benchmark)	12.46	source
RTX 4060 Ti 16GB: 2026 models (llamabench community)	llama-bench tg128 (quant per result)	llama.cpp	10.7-17.6	source
RTX 3060 12GB: 2026 models (llamabench community)	llama-bench tg128 (quant per result)	llama.cpp	5.2-6.7	source

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

Rent before you buy: try this model on a cloud GPU for a few dollars first: RunPod

FAQ

How much VRAM does Qwen3.8 27B need?

The weights are about 16.5 GB at Q4_K_M (27B params × 4.89 bits ÷ 8, before context/KV cache). Add memory for context (KV cache) and the runtime. The smallest-memory setup with a measured result here, fully in memory, is RTX 3090 (24 GB) at 139.7 tok/s.

What is the fastest measured hardware for Qwen3.8 27B?

RTX 3090: 139.7 tok/s generation (OpenJet megakernel (MTP, 4 drafts), Q4_K_M (unsloth), greedy code prompt), from https://github.com/L-Forster/open-jet/tree/master/megakernel.

Which GPUs have measured results for Qwen3.8 27B?

2x Apple M5 Ultra, 4x Apple M5 Ultra, Apple M3 Ultra, Apple M5 Ultra, RTX 3060 12GB, RTX 3090, RTX 4060 Ti 16GB, RTX Spark N1X.

Can it run on… 2x Apple M5 Ultra · 4x Apple M5 Ultra · Apple M3 Ultra · Apple M5 Ultra · RTX 3060 12GB · RTX 3090 · RTX 4060 Ti 16GB · RTX Spark N1X