← CanIRunLocal · All hardware · All models
Yes, if the Mac GPU limit is raised. Qwen3-Next 80B-A3B (MoE) on M2 Max (38c GPU) 64GB at Q4_K_M needs sudo sysctl iogpu.wired_limit_mb=55706 (52.4 GB needed, 48.0 GB usable), about 85 tok/s (estimate).
Hardware: M2 Max (38c GPU) 64GB · Model: Qwen3-Next 80B-A3B (MoE)
M2 Max (38c GPU) 64GB has 64 GB of unified memory and 400 GB/s of memory bandwidth. M1 Max (32c GPU) 64GB and M2 Max (30c GPU) 64GB and M3 Max (40c GPU) 64GB have the same memory and bandwidth, so the fit numbers match; this page is M2 Max (38c GPU) 64GB. The checker leaves macOS a share of unified memory, so Ollama can use 48.0 GB. Qwen3-Next 80B-A3B (MoE) (80B, 3B active, Alibaba) at Q4_K_M is a 50 GB download and needs 52.4 GB with headroom for about 8k tokens.
| Best quant | Q4_K_M |
|---|---|
| Download size | 50 GB |
| Memory needed | 52.4 GB |
| Usable fast memory | 48.0 GB |
| Fit | fits if the Mac GPU limit is raised |
| Estimated speed | ~85 tok/s (estimate) |
| Mac GPU limit | sudo sysctl iogpu.wired_limit_mb=55706 |
| Command | ollama run qwen3-next:80b |
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