← CanIRunLocal · All hardware · All models
No. Granite 4.2 8B does not fit on M2 8GB: Q4_K_M needs 6.3 GB and 5.4 GB is usable.
Hardware: M2 8GB · Model: Granite 4.2 8B
M2 8GB has 8 GB of unified memory and 100 GB/s of memory bandwidth. M3 8GB has the same memory and bandwidth, so the fit numbers match; this page is M2 8GB. The checker leaves macOS a share of unified memory, so Ollama can use 5.4 GB. Granite 4.2 8B (8.79B, IBM) at Q4_K_M is a 5.3 GB download and needs 6.3 GB with headroom for about 8k tokens.
| Best quant | Q4_K_M |
|---|---|
| Download size | 5.3 GB |
| Memory needed | 6.3 GB |
| Usable fast memory | 5.4 GB |
| Fit | does not fit |
| Estimated speed | no estimate, it does not fit |
| Command | ollama run granite4.2:8b |
Smallest hardware that runs it: RTX 3060 8GB at Q5_K_M (fits in fast memory, 7.3 GB needed, 7.5 GB usable, about 23 tok/s (estimate)). Can a RTX 3060 8GB run Granite 4.2 8B?
A smaller IBM model that fits this hardware: Granite 4.2 3B at Q8_0 (fits in fast memory, 4.7 GB). Can a M2 8GB run Granite 4.2 3B?
Open M2 8GB 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