Can RTX 3090 run Qwen3.8 27B?

Q: Can RTX 3090 run Qwen3.8 27B?

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

Yes. Measured 139.7 tok/s generation (OpenJet megakernel (MTP, 4 drafts), Q4_K_M (unsloth), greedy code prompt; source).

Every measured result for Qwen3.8 27B on RTX 3090

Build	Quant / setup	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
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

Memory: RTX 3090 has 24 GB. Qwen3.8 27B weights are about 16.5 GB at Q4_K_M (27B params × 4.89 bits ÷ 8, before context/KV cache). Arithmetic, not a measurement; long contexts need more. Check other quants in the VRAM calculator.

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 · 2x Intel Arc Pro B70 · 2x RTX 5070 Ti · 2x Tesla V100 32GB · 4x Apple M5 Ultra · Apple M3 Ultra · Apple M5 Ultra · DGX Spark (GB10) · Intel Arc Pro B70 · RTX 3060 12GB · RTX 4060 Ti 16GB · RTX 5070 Ti · RTX 5090 · RTX Pro 6000 Max-Q (Blackwell, 96 GB, 300 W) · RTX Spark N1X · Radeon AI Pro R9700 · Strix Halo (Radeon 8060S)

Other models measured on RTX 3090: DeepSeek R1 671B · Flint 40B-A2.5B · GLM 4.7 Flash · Qwen3.6 27B · Qwen3.6 35B-A3B · gpt-oss 20B

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: if you sign up with Google and add $10, Runpod gives you and RigBase bonus credit (terms). It never affects our data.