Dual Intel Arc Pro B70 (neural.download lab)
| GPU(s) | 2x Intel Arc Pro B70 32 GB Amazon · eBay (used) · Newegg |
|---|---|
| VRAM / unified memory (GB) | 64 |
| CPU | |
| Motherboard | |
| RAM | |
| PSU | |
| Other | Lab Linux host; SYCL |
| Reported total cost | |
| Power |
Measured speed (generation tokens/sec)
📏 How measured: reported by the original source; RigBase re-checked the numbers at that source
| Model | Quant | Engine | tok/s | Details |
|---|---|---|---|---|
| Qwen3.8 Flash-Next | IQ3 | neural.download runtime, TP2 | 58.56 | 📏 Lab README/scoreboard |
| Qwen3.8 27B | FP8 | vLLM XPU, TP2, MTP 5 | 46.01 | ⚡ spec-decode (MTP)📏 Lab README/scoreboard |
From the lab README/scoreboard. TP1 on the same Flash-Next build: 31.5-31.8 tok/s. An older 90.3 tok/s 27B FP8 receipt did not reproduce and is excluded. Found via localmaxxing (discovery only); numbers re-checked at the original source on 2026-10-24.
Source: https://github.com/steveseguin/b70-optimization-lab
Blank fields = not stated in the source. We never estimate build data; GPU street prices above are separately sourced and dated.
Rent before you buy: try this model on a cloud GPU for a few dollars first: Runpod (referral link; sign up with Google to get the new-user bonus)
Quick answers: Can 2x Intel Arc Pro B70 run Qwen3.8 27B? · Can 2x Intel Arc Pro B70 run Qwen3.8 Flash-Next?