← CanIRunLocal · All hardware · All models
No. Qwen3 235B-A22B (MoE) does not fit on Mac Studio M3 Ultra (80c GPU) 96GB: Q4_K_M needs 144.3 GB and 72.0 GB is usable.
Hardware: Mac Studio M3 Ultra (80c GPU) 96GB · Model: Qwen3 235B-A22B (MoE)
Mac Studio M3 Ultra (80c GPU) 96GB has 96 GB of unified memory and 819 GB/s of memory bandwidth. Mac Studio M3 Ultra (60c GPU) 96GB has the same memory and bandwidth, so the fit numbers match; this page is Mac Studio M3 Ultra (80c GPU) 96GB. The checker leaves macOS a share of unified memory, so Ollama can use 72.0 GB. Qwen3 235B-A22B (MoE) (235B, 22B active, Alibaba) at Q4_K_M is a 142 GB download and needs 144.3 GB with headroom for about 8k tokens.
| Best quant | Q4_K_M |
|---|---|
| Download size | 142 GB |
| Memory needed | 144.3 GB |
| Usable fast memory | 72.0 GB |
| Fit | does not fit |
| Estimated speed | no estimate, it does not fit |
| Command | ollama run qwen3:235b |
Smallest hardware that runs it: M2 Ultra 192GB at Q4_K_M (fits if the Mac GPU limit is raised, 144.3 GB needed, 144.0 GB usable, about 24 tok/s (estimate)). Can a M2 Ultra 192GB run Qwen3 235B-A22B (MoE)?
A smaller Alibaba model that fits this hardware: Qwen3.5 122B-A10B (MoE) at Q4_K_M (fits if the Mac GPU limit is raised, 83.7 GB). Can a Mac Studio M3 Ultra (80c GPU) 96GB run Qwen3.5 122B-A10B (MoE)?
Open Mac Studio M3 Ultra (80c GPU) 96GB in the checkerEstimates, 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