More
Best rig by budgetRent before you buySubmit a buildNewsletterFree datasetAdvertise
Submit build

Can 2x DGX Spark (GB10) run Qwen3.8 27B?

Last updated:

Yes. Measured 44.7 tok/s generation (vLLM 0.1.dev20003 TP2, MTP n=3, FP8 KV, 351K context, NVFP4 (Unsloth, 4-bit, 23.4 GB on disk); source).

Every measured result for Qwen3.8 27B on 2x DGX Spark (GB10)

BuildQuant / setupEnginetok/s
2x DGX Spark (GB10, 2,200 MHz cap): Qwen3.8 27B NVFP4 at 44.7 tok/s code / 2,034 prefill (vLLM TP2)NVFP4 (Unsloth, 4-bit, 23.4 GB on disk)vLLM 0.1.dev20003 TP2, MTP n=3, FP8 KV, 351K context44.7source

Memory: 2x DGX Spark (GB10) has 256 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 3060 12GB · 2x RTX 3090 · 2x RTX 5070 Ti · 2x Tesla V100 32GB · 4x Apple M5 Ultra · Apple M2 Ultra · Apple M3 Ultra · Apple M5 Ultra · DGX Spark (GB10) · Intel Arc Pro B70 · RTX 3060 12GB · RTX 3090 · RTX 4060 Ti 16GB · RTX 4090 · RTX 5060 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 2x DGX Spark (GB10): DeepSeek V4 Flash · DeepSeek V4.1 Flash · GLM-5.3 Flash · MiMo V2.6 Flash · MiniMax M3.1 Flash · Qwen3.8 Flash-Next

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.