Can RTX Spark N1X run Gemma 4 26B-A4B?

Q: Can RTX Spark N1X run Gemma 4 26B-A4B?

Yes. Measured 60.7 tok/s generation on RTX Spark N1X, via llama.cpp b11669 (CUDA, Windows on Arm), UD-IQ4_XS (13.6 GB). Source: https://measuredlocally.com/rtx-spark.html

Last updated: 2 Nov 2026

Yes. Measured 60.7 tok/s generation (llama.cpp b11669 (CUDA, Windows on Arm), UD-IQ4_XS (13.6 GB); source).

Every measured result for Gemma 4 26B-A4B on RTX Spark N1X

Build	Quant / setup	Engine	tok/s
Lenovo Yoga Pro 9n (RTX Spark, 128 GB): gpt-oss 20B at 80.4 tok/s, Qwen3.6 35B-A3B at 72.1 (llama.cpp CUDA, Windows on Arm)	UD-IQ4_XS (13.6 GB)	llama.cpp b11669 (CUDA, Windows on Arm)	60.7	source

Memory: RTX Spark N1X 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: DGX Spark (GB10) · Intel Arc Pro B70 · RTX 4090 · RTX 5070 Ti · RTX 5090 · Strix Halo (Radeon 8060S)

Other models measured on RTX Spark N1X: GLM 4.7 Flash · Gemma 4 12B · Muse Glimmer 30B · Nemotron 3 Nano Omni 30B · Qwen3.5 122B · Qwen3.5 9B · Qwen3.6 35B-A3B · Qwen3.8 27B · Qwen3.8 Flash-Next · 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.