← CanIRunLocal · All hardware · All models
No. LFM2.5 24B-A2B (MoE) does not fit on M4 24GB: Q4_K_M needs 16.2 GB and 16.1 GB is usable.
Hardware: M4 24GB · Model: LFM2.5 24B-A2B (MoE)
M4 24GB has 24 GB of unified memory and 120 GB/s of memory bandwidth. The checker leaves macOS a share of unified memory, so Ollama can use 16.1 GB. LFM2.5 24B-A2B (MoE) (24B, 2B active, Liquid AI) at Q4_K_M is a 15 GB download and needs 16.2 GB with headroom for about 8k tokens.
| Best quant | Q4_K_M |
|---|---|
| Download size | 15 GB |
| Memory needed | 16.2 GB |
| Usable fast memory | 16.1 GB |
| Fit | does not fit |
| Estimated speed | no estimate, it does not fit |
| Command | ollama run lfm2.5:24b |
Smallest hardware that runs it: RTX 3060 8GB at Q4_K_M (partial offload (slower), 16.2 GB needed, 7.5 GB usable, about 24 tok/s (estimate)). Can a RTX 3060 8GB run LFM2.5 24B-A2B (MoE)?
A smaller Liquid AI model that fits this hardware: LFM2.5 8B-A1B (MoE) at Q8_0 (fits in fast memory, 9.8 GB). Can a M4 24GB run LFM2.5 8B-A1B (MoE)?
Open M4 24GB 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