← CanIRunLocal · All hardware · All models
No. Qwen3-Next 80B-A3B (MoE) does not fit on M3 Max (30c GPU) 36GB: Q4_K_M needs 52.4 GB and 27.0 GB is usable.
Hardware: M3 Max (30c GPU) 36GB · Model: Qwen3-Next 80B-A3B (MoE)
M3 Max (30c GPU) 36GB has 36 GB of unified memory and 300 GB/s of memory bandwidth. The checker leaves macOS a share of unified memory, so Ollama can use 27.0 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 | 27.0 GB |
| Fit | does not fit |
| Estimated speed | no estimate, it does not fit |
| Command | ollama run qwen3-next:80b |
Smallest hardware that runs it: M1 Max (32c GPU) 64GB at Q4_K_M (fits if the Mac GPU limit is raised, 52.4 GB needed, 48.0 GB usable, about 85 tok/s (estimate)). Can a M1 Max (32c GPU) 64GB run Qwen3-Next 80B-A3B (MoE)?
A smaller Alibaba model that fits this hardware: Qwen3.5 35B-A3B (MoE) at Q4_K_M (fits in fast memory, 23.9 GB). Can a M3 Max (30c GPU) 36GB run Qwen3.5 35B-A3B (MoE)?
Open M3 Max (30c GPU) 36GB 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