Builds / Apple M4 Pro (unified, MacBook Pro)
MacBook Pro M4 Pro 24 GB: Qwen3.8 27B GSQ IQ3_S (12.1 GB) on llama.cpp Metal at 11.4 tok/s, MTP gives no gain (Kingy)
Last updated:
Source: kingy.ai ↗📏 How measured: reported by the original source; RigBase re-checked the numbers at that source
- GPU(s)
- Apple M4 Pro (unified, MacBook Pro)
- VRAM / unified memory (GB)
- 24
- CPU
- Apple M4 Pro
- Motherboard
- MacBook Pro
Amazon · eBay (used) · Newegg - RAM
- 24 GB unified
- PSU
- not stated
- Other
- llama.cpp 0.6.0 from Homebrew (Metal), whole model fits
- 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 | GSQ-RCO IQ3_S + MTP head (ISTA-DASLab GGUF, 12.12 GB) | llama.cpp 0.6.0 (Metal) | 11.4 | not stated | context: 32K ctx, one request at a time📏 Kingy test 8 Nov 2026: llama-server, 32K ctx, prompt cache off, temperature 0, seed 42, up to 1,024 reply tokens (all spent thinking); average of 4 prompts (code, explainer, HTML report, question on an 8,217-token document); MTP off; llama-bench tg128 12.3 (10.9 with 8K in context); about 82-87 s before the first token on the 8K document |
| Qwen3.8 27B | GSQ-RCO IQ3_S + MTP head (ISTA-DASLab GGUF, 12.12 GB) | llama.cpp 0.6.0 (Metal) | 10.9 | not stated | ⚡ spec-decode (MTP)context: 32K ctx, one request at a time📏 Kingy test 8 Nov 2026: llama-server, 32K ctx, prompt cache off, temperature 0, seed 42, up to 1,024 reply tokens (all spent thinking); average of 4 prompts (code, explainer, HTML report, question on an 8,217-token document); --spec-type draft-mtp --spec-draft-n-max 2; 70% of drafts kept but no speed gain on this Mac |
Owner-run test by Kingy (8 Nov 2026). Caveat from the source: the Mac had 7-16 GB of swap in use from other apps and ran partly on battery, so a clean Mac should be somewhat faster; each prompt ran once. Kingy's 20-task quality test ran on this Mac: the GSQ IQ3_S file scored 20/20.
Source: https://kingy.ai/blog/qwen3-8-27b-gsq-tested/
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 Apple M4 Pro run Qwen3.8 27B?
Speculative-decoding rows on this page are not like-for-like with plain decode. See how much MTP and DFlash really speed things up (measured pairs).