← CanIRunLocal · All hardware · All models
No. Nemotron 3.5 Super 120B-A12B (MoE) does not fit on M2 Max (38c GPU) 96GB: Q4_K_M needs 92.7 GB and 72.0 GB is usable.
Hardware: M2 Max (38c GPU) 96GB · Model: Nemotron 3.5 Super 120B-A12B (MoE)
M2 Max (38c GPU) 96GB has 96 GB of unified memory and 400 GB/s of memory bandwidth. The checker leaves macOS a share of unified memory, so Ollama can use 72.0 GB. Nemotron 3.5 Super 120B-A12B (MoE) (120B, 12B active, NVIDIA) at Q4_K_M is a 90 GB download and needs 92.7 GB with headroom for about 8k tokens.
| Best quant | Q4_K_M |
|---|---|
| Download size | 90 GB |
| Memory needed | 92.7 GB |
| Usable fast memory | 72.0 GB |
| Fit | does not fit |
| Estimated speed | no estimate, it does not fit |
| Command | ollama run nemotron-3.5-super:120b-a12b-q4_K_M |
Smallest hardware that runs it: M2 Ultra 128GB at Q4_K_M (fits in fast memory, 92.7 GB needed, 96.0 GB usable, about 36 tok/s (estimate)). Can a M2 Ultra 128GB run Nemotron 3.5 Super 120B-A12B (MoE)?
A smaller NVIDIA model that fits this hardware: Nemotron 3.5 Bolt 74B-A9B (MoE, IQ2-class) at Default (fits in fast memory, 27.7 GB). Can a M2 Max (38c GPU) 96GB run Nemotron 3.5 Bolt 74B-A9B (MoE, IQ2-class)?
Open M2 Max (38c 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