Can Intel Arc Pro B70 run Qwen3.5 9B?
Last updated:
Yes. Measured 66.5 tok/s generation (llama.cpp b12128 (SYCL), Q6_K; source).
Every measured result for Qwen3.5 9B on Intel Arc Pro B70
| Build | Quant / setup | Engine | tok/s | |
|---|---|---|---|---|
| Intel Arc Pro B70 32 GB (Core i7-12700KF, llama.cpp b12128 SYCL): gpt-oss 20B MXFP4 at 134.2 tok/s, Gemma 4 E4B Q4_K_M 97.3, Qwen3.5 9B Q6_K 66.5 | Q6_K | llama.cpp b12128 (SYCL) | 66.5 | source |
Memory: Intel Arc Pro B70 has 32 GB. Qwen3.5 9B weights are about 5.5 GB at Q4_K_M (8.95B 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 Qwen3.5 9B: best home rig for Qwen3.5 9B.
Qwen3.5 9B on other hardware: Apple M4 · RTX 4090 · RTX 5070 Ti · RTX 5090 · RTX Spark N1X · Strix Halo (Radeon 8060S)
Other models measured on Intel Arc Pro B70: Gemma 4 26B-A4B · Ornith 1.5 35B-A3B · Qwen3.6 35B-A3B · Qwen3.8 27B · gpt-oss 20B
Not enough VRAM? Rent before you buy. Run Qwen3.5 9B 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.