← CanIRunLocal · All hardware · All models
Yes. Qwen3-Next 80B-A3B (MoE) fits in fast memory on M3 Max (30c GPU) 96GB at Q4_K_M (52.4 GB needed, 72.0 GB usable), about 64 tok/s (estimate).
Hardware: M3 Max (30c GPU) 96GB · Model: Qwen3-Next 80B-A3B (MoE)
M3 Max (30c GPU) 96GB has 96 GB of unified memory and 300 GB/s of memory bandwidth. The checker leaves macOS a share of unified memory, so Ollama can use 72.0 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 | 72.0 GB |
| Fit | fits in fast memory |
| Estimated speed | ~64 tok/s (estimate) |
| 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