Builds / 2x Intel Arc Pro B60 24GB (Maxsun Arc Pro B60 Dual 48G Turbo
2x Intel Arc Pro B60 (Maxsun Dual 48G): Qwen3.8 27B Q4_K_L at 16.1 tok/s, 24.0 with MTP (SYCL)
Last updated:
- GPU(s)
- 2x Intel Arc Pro B60 24GB (Maxsun Arc Pro B60 Dual 48G Turbo, one board)
Amazon · eBay (used) · Newegg - VRAM / unified memory (GB)
- 48
- CPU
- not stated
- Motherboard
- not stated
- RAM
- not stated
- PSU
- not stated
- Other
- Windows 11 Pro; llama.cpp SYCL (F16 JIT, oneDNN, Level-Zero), oneAPI 2026.1.1; split-mode layer, -ts 1.25/0.75
- Reported total cost
- not stated
- Power
- not stated
Measured speed (generation tokens/sec)
| Model | Quant | Engine | tok/s | Prompt processing (tok/s) | Details |
|---|---|---|---|---|---|
| Qwen3.8 27B | Q4_K_L (Swift-Qwen3.8-27B GGUF, 17.72 GiB), no MTP | llama.cpp b11100 (7ab4ee7b) SYCL | 16.13 | not stated | context: 131K ctx allocated📏 "Stock non-MTP decode" as stated in the submission notes |
| Qwen3.8 27B | Q4_K_L (Swift-Qwen3.8-27B GGUF) + embedded Q8_0 MTP head, KV q8_0 | llama.cpp b11100 (7ab4ee7b) SYCL, --spec-type draft-mtp, n_max 3 | 24.0 | 609 @ 512-token prompt est. TTFT @8k ≈ 13.4 s (calculated from measured prefill) measured TTFT: 0.84 s @ 512-token prompt | ⚡ spec-decode (MTP)context: 131K ctx allocated, batch 1📏 Submitted decode figure; the submitter sees 20-30 t/s across context lengths in chat |
Prompt processing = prefill speed (how fast the prompt is read) as reported by the source, with the prompt length it was measured at; blank = the source does not report it. est. TTFT @8k is calculated from the measured prefill speed (8,192 ÷ prefill tok/s), shown only when prefill was measured on a prompt of 512+ tokens. It is not a measurement and ignores load time and caching. measured TTFT is the source's own time-to-first-token. Why prefill matters for coding assistants.
Self-reported community result on intelinside.ai by nulliik, run 22 Sep 2026. Swift-Qwen3.8-27B is a community GGUF of Qwen3.8 27B with an embedded MTP head.
Blank fields = not stated in the source. We never estimate build data; GPU street prices above are separately sourced and dated.
Copy into a README or blog. Links back to this build. See badge docs (CC BY 4.0 attribution). The SVG does not invent speeds — numbers stay on the build page.
Markdown
[](https://getrigbase.com/builds/2x-arc-pro-b60-maxsun-dual-48gb-qwen38-27b-sycl-mtp/)
HTML
<a href="https://getrigbase.com/builds/2x-arc-pro-b60-maxsun-dual-48gb-qwen38-27b-sycl-mtp/" rel="noopener"><img src="https://getrigbase.com/badge/2x-arc-pro-b60-maxsun-dual-48gb-qwen38-27b-sycl-mtp.svg" alt="Measured on RigBase" height="20"/></a>
Preview: 
· How to use