← CanIRunLocal · All hardware · All models
No. Llama 3.1 8B does not fit on M1 8GB: Q4_K_M needs 5.9 GB and 5.4 GB is usable.
Hardware: M1 8GB · Model: Llama 3.1 8B
M1 8GB has 8 GB of unified memory and 68 GB/s of memory bandwidth. The checker leaves macOS a share of unified memory, so Ollama can use 5.4 GB. Llama 3.1 8B (8.03B, Meta) at Q4_K_M is a 4.9 GB download and needs 5.9 GB with headroom for about 8k tokens.
| Best quant | Q4_K_M |
|---|---|
| Download size | 4.9 GB |
| Memory needed | 5.9 GB |
| Usable fast memory | 5.4 GB |
| Fit | does not fit |
| Estimated speed | no estimate, it does not fit |
| Command | ollama run llama3.1:8b |
Smallest hardware that runs it: RTX 3060 8GB at Q5_K_M (fits in fast memory, 6.7 GB needed, 7.5 GB usable, about 25 tok/s (estimate)). Can a RTX 3060 8GB run Llama 3.1 8B?
A smaller Meta model that fits this hardware: Code Llama 7B at Q4_K_M (fits in fast memory, 5 GB). Can a M1 8GB run Code Llama 7B?
Open M1 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