Can DGX Spark (GB10) run Gemma 4 26B-A4B?

Q: Can DGX Spark (GB10) run Gemma 4 26B-A4B?

Yes. Measured 56.5 tok/s generation on DGX Spark (GB10), via vLLM 0.31.0, 128K ctx, 1 user, + official MTP drafter (k=3). Source: https://ctala.github.io/local-llm-agentic-workflows/benchmarks/

Yes. Measured 56.5 tok/s generation (vLLM 0.31.0, 128K ctx, 1 user, + official MTP drafter (k=3); source).

Every measured result for Gemma 4 26B-A4B on DGX Spark (GB10)

Build	Quant / setup	Engine	tok/s
DGX Spark (GB10, 128 GB): 23 models on vLLM at 128K context, Qwen3.6 35B-A3B up to 102 tok/s	+ official MTP drafter (k=3)	vLLM 0.31.0, 128K ctx, 1 user	56.5	source
DGX Spark (GB10, 128 GB): 23 models on vLLM at 128K context, Qwen3.6 35B-A3B up to 102 tok/s	no speculative decoding	vLLM 0.31.0, 128K ctx, 1 user	30.8	source

Memory: DGX Spark (GB10) has 128 GB. Gemma 4 26B-A4B weights are about 15.4 GB at Q4_K_M (25.23B 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 Gemma 4 26B-A4B: best home rig for Gemma 4 26B-A4B.

Gemma 4 26B-A4B on other hardware: Intel Arc Pro B70 · RTX 4090 · RTX 5090 · Strix Halo (Radeon 8060S)

Other models measured on DGX Spark (GB10): 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 27B · 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 Gemma 4 26B-A4B 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.