Can DGX Spark (GB10) run Qwen3.6 27B?

Q: Can DGX Spark (GB10) run Qwen3.6 27B?

Yes. Measured 32.83 tok/s generation on DGX Spark (GB10), via vLLM + DFlash spec decoding, NVFP4. Source: https://github.com/my-other-github-account/qwen36-dflash-spark-repro

Yes. Measured 32.83 tok/s generation (vLLM + DFlash spec decoding, NVFP4; source).

Every measured result for Qwen3.6 27B on DGX Spark (GB10)

Build	Quant / setup	Engine	tok/s
DGX Spark with Qwen3.6 27B NVFP4 + DFlash speculative decoding	NVFP4	vLLM + DFlash spec decoding	32.83	source
DGX Spark with Qwen3.6 27B NVFP4 + DFlash speculative decoding	FP8	vLLM autoregressive baseline	7.85	source

Memory: DGX Spark (GB10) has 128 GB. Qwen3.6 27B weights are about 16.7 GB at Q4_K_M (27.32B 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 Qwen3.6 27B: best home rig for Qwen3.6 27B.

Qwen3.6 27B on other hardware: RTX 3090 · RTX 4090 · RTX 5090 · Radeon AI Pro R9700 · Strix Halo (Radeon 8060S)

Other models measured on DGX Spark (GB10): Gemma 4 26B-A4B · Nemotron 3 Nano Omni 30B · Nemotron 3 Super 120B-A12B · Nemotron 3.5 Bolt 74B-A9B · Nemotron 3.5 Lightning 30B-A3B · Nemotron 3.5 Super VL 120B-A12B · Qwen3.6 35B-A3B · Qwen3.8 27B · Qwen3.8 Flash-Next · gpt-oss 120B · gpt-oss 20B

Not enough VRAM? Rent before you buy. Run Qwen3.6 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.