← CanIRunLocal · All hardware · All models
No. Flint 40B-A2.5B (MoE) does not fit on M2 Max (38c GPU) 32GB: NVFP4 needs 24.6 GB and 24.0 GB is usable.
Hardware: M2 Max (38c GPU) 32GB · Model: Flint 40B-A2.5B (MoE)
M2 Max (38c 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 (30c GPU) 32GB have the same memory and bandwidth, so the fit numbers match; this page is M2 Max (38c GPU) 32GB. The checker leaves macOS a share of unified memory, so Ollama can use 24.0 GB. Flint 40B-A2.5B (MoE) (39.8B, 2.5B active, Recursive) at NVFP4 is a 23 GB download and needs 24.6 GB with headroom for about 8k tokens.
| Best quant | NVFP4 |
|---|---|
| Download size | 23 GB |
| Memory needed | 24.6 GB |
| Usable fast memory | 24.0 GB |
| Fit | does not fit |
| Estimated speed | no estimate, it does not fit |
| Command | ollama run flint:40b |
Smallest hardware that runs it: RTX 4060 Ti 16GB at NVFP4 (partial offload (slower), 24.6 GB needed, 15.5 GB usable, about 27 tok/s (estimate)). Can a RTX 4060 Ti 16GB run Flint 40B-A2.5B (MoE)?
No smaller Recursive model in this list fits M2 Max (38c GPU) 32GB.
Open M2 Max (38c 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