← CanIRunLocal · All hardware · All models
Yes. DeepSeek Coder V2 Lite 16B (MoE) fits in fast memory on M2 24GB at Q5_K_M (13 GB needed, 16.1 GB usable), about 22 tok/s (estimate).
Hardware: M2 24GB · Model: DeepSeek Coder V2 Lite 16B (MoE)
M2 24GB has 24 GB of unified memory and 100 GB/s of memory bandwidth. M3 24GB has the same memory and bandwidth, so the fit numbers match; this page is M2 24GB. The checker leaves macOS a share of unified memory, so Ollama can use 16.1 GB. DeepSeek Coder V2 Lite 16B (MoE) (15.7B, 2.4B active, DeepSeek) at Q5_K_M is a 12 GB download and needs 13 GB with headroom for about 8k tokens.
| Best quant | Q5_K_M |
|---|---|
| Download size | 12 GB |
| Memory needed | 13 GB |
| Usable fast memory | 16.1 GB |
| Fit | fits in fast memory |
| Estimated speed | ~22 tok/s (estimate) |
| Command | ollama run deepseek-coder-v2:16b-lite-instruct-q5_K_M |
Estimates, 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