Builds / Apple M4 Pro (unified)
Mac mini M4 Pro 24 GB: Qwen3.8 Flash-Next (125B-A6B) IQ3_XXS at 10.7 tok/s, 9.4 after a 6K prompt (MoEShift, SSD experts)
Last updated:
- GPU(s)
- Apple M4 Pro (unified)
- VRAM / unified memory (GB)
- 24
- CPU
- Apple M4 Pro
- Motherboard
- Mac mini
Amazon · eBay (used) · Newegg - RAM
- 24 GB unified
- PSU
- not stated
- Other
- macOS 27.2.1, MoEShift v0.1.0-alpha.5 built from source (a9f103c), default 24 GB config (ctx 65536, prefill bank 512, 24 protected slots); headless, mains power, no other model loaded
- 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 Flash-Next | ISTA-DASLab GSQ-RCO IQ3_XXS (~76 GB, 2 shards), experts streamed from the internal SSD | MoEShift 0.1.0-alpha.5 (llama.cpp-based, Metal) | 10.74 | 20.3 @ 72-token prompt | context: 72-token prompt, 512 generated (64K ctx configured)📏 moeshift-community-v1 protocol: median of 3 measured runs after 1 warm-up, 512 output tokens, prompt cache off (cache_n 0); short-prompt generation runs 10.74-10.78 |
| Qwen3.8 Flash-Next | ISTA-DASLab GSQ-RCO IQ3_XXS (~76 GB, 2 shards), experts streamed from the internal SSD | MoEShift 0.1.0-alpha.5 (llama.cpp-based, Metal) | 9.38 | 199 @ 6K-token prompt est. TTFT @8k ≈ 41.2 s (calculated from measured prefill) | context: 6,060-token prompt, 512 generated📏 moeshift-community-v1 protocol: median of 3 measured runs after 1 warm-up, 512 output tokens, prompt cache off (cache_n 0); long-prompt runs 9.37-9.38, prefill 197.2-199.9 |
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.
Filed 18 Nov 2026 (moeshift issue #15). Community report filed on the MoEShift GitHub tracker (MoEShift is an open-source llama.cpp-based engine for Apple Silicon that keeps the shared weights in memory and streams Mixture-of-Experts weights from the SSD as they are needed). It lets the 125B-A6B Qwen3.8 Flash-Next run on Macs with far less memory than the ~76 GB file. Speed depends on SSD speed and expert cache hits, so expect variation. IQ3_XXS is below Q4.
https://github.com/davide-troiani/moeshift
Blank fields = not stated in the source. We never estimate build data; GPU street prices above are separately sourced and dated.
Quick answers: Can Apple M4 Pro run Qwen3.8 Flash-Next?