Can Intel Arc Pro B70 run Gemma 4 26B-A4B?
Yes. Measured 122.16 tok/s generation (llama.cpp SYCL (pinned build, oneAPI 2026.0), UD-Q8_K_XL; source).
Every measured result for Gemma 4 26B-A4B on Intel Arc Pro B70
| Build | Quant / setup | Engine | tok/s | |
|---|---|---|---|---|
| Single Intel Arc Pro B70 32 GB (neural.download lab) | UD-Q8_K_XL | llama.cpp SYCL (pinned build, oneAPI 2026.0) | 122.16 | source |
Memory: Intel Arc Pro B70 has 32 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) · RTX 4090 · RTX 5090 · Strix Halo (Radeon 8060S)
Other models measured on Intel Arc Pro B70: Ornith 1.5 35B-A3B · Qwen3.6 35B-A3B · Qwen3.8 27B
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.
Referral link: if you sign up with Google and add $10, Runpod gives you and RigBase bonus credit (terms). It never affects our data.