← CanIRunLocal · All hardware · All models
No. gpt-oss 120B (MoE, MXFP4) does not fit on M2 Max (30c GPU) 32GB: MXFP4 needs 67.3 GB and 24.0 GB is usable.
Hardware: M2 Max (30c GPU) 32GB · Model: gpt-oss 120B (MoE, MXFP4)
M2 Max (30c GPU) 32GB has 32 GB of unified memory and 400 GB/s of memory bandwidth. M1 Max (24c GPU) 32GB and M1 Max (32c GPU) 32GB and M2 Max (38c GPU) 32GB have the same memory and bandwidth, so the fit numbers match; this page is M2 Max (30c GPU) 32GB. The checker leaves macOS a share of unified memory, so Ollama can use 24.0 GB. gpt-oss 120B (MoE, MXFP4) (117B, 5.1B active, OpenAI) at MXFP4 is a 65 GB download and needs 67.3 GB with headroom for about 8k tokens.
| Best quant | MXFP4 |
|---|---|
| Download size | 65 GB |
| Memory needed | 67.3 GB |
| Usable fast memory | 24.0 GB |
| Fit | does not fit |
| Estimated speed | no estimate, it does not fit |
| Command | ollama run gpt-oss:120b |
Smallest hardware that runs it: M2 Max (38c GPU) 96GB at MXFP4 (fits in fast memory, 67.3 GB needed, 72.0 GB usable, about 56 tok/s (estimate)). Can a M2 Max (38c GPU) 96GB run gpt-oss 120B (MoE, MXFP4)?
A smaller OpenAI model that fits this hardware: gpt-oss 20B (MoE, MXFP4) at MXFP4 (fits in fast memory, 15.1 GB). Can a M2 Max (30c GPU) 32GB run gpt-oss 20B (MoE, MXFP4)?
Open M2 Max (30c GPU) 32GB 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