← CanIRunLocal · All hardware · All models
Yes. Qwen3.8-Flash-Next 125B-A6B (MoE) fits in fast memory on Mac Studio M5 Ultra (80c GPU) 256GB at Q8_0 (191.7 GB needed, 192.0 GB usable), about 53 tok/s (estimate).
Hardware: Mac Studio M5 Ultra (80c GPU) 256GB · Model: Qwen3.8-Flash-Next 125B-A6B (MoE)
Mac Studio M5 Ultra (80c GPU) 256GB has 256 GB of unified memory and 1200 GB/s of memory bandwidth. Mac Studio M5 Ultra (64c GPU) 256GB has the same memory and bandwidth, so the fit numbers match; this page is Mac Studio M5 Ultra (80c GPU) 256GB. The checker leaves macOS a share of unified memory, so Ollama can use 192.0 GB. Qwen3.8-Flash-Next 125B-A6B (MoE) (125B, 6B active, Alibaba) at Q8_0 is a 189 GB download and needs 191.7 GB with headroom for about 8k tokens.
| Best quant | Q8_0 |
|---|---|
| Download size | 189 GB |
| Memory needed | 191.7 GB |
| Usable fast memory | 192.0 GB |
| Fit | fits in fast memory |
| Estimated speed | ~53 tok/s (estimate) |
| Command | ollama run qwen3.8-flash-next:125b-a6b-q8_0 |
Estimates, not benchmarks. Model sizes are ollama.com download sizes; memory needed adds headroom for ~8k tokens of context; speeds are rough figures from memory bandwidth. Data updated 2026-10-23.
A project by OnDevice Labs · llms.txt