Yes — with 18.5 GB to spare
LFM2.5 8B-A1B at Q4_K_M fits your M2 Pro · 32 GB entirely in unified memory at 8K context, at an estimated 62 tokens per second. There is room for its full 125K window.
Fully in unified memory
8K context
Q4_K_M · 4.8 GB
LFM Open License v1.0
Released 28 May 2026
An 8B MoE with ~1.5B active, aimed at laptops without a GPU. Licence is permissive below $10M revenue.
The VRAM budget
weights 4.8 GB
Weights 4.8 GB
KV cache @ 8K 0.09 GB
Runtime overhead 0.6 GB
Free 18.5 GB of 24.0 GB
Quantisation ladder
| Quant | Weights | Total @ 8K | Max context | Tok/s | Quality | Fit |
|---|---|---|---|---|---|---|
| F16 | 15.8 GB | 16.5 GB | 125K | 19 | Reference | Long context |
| Q8_0 | 8.4 GB | 9.1 GB | 125K | 35 | −0.1% ppl | Long context |
| Q6_K | 6.5 GB | 7.2 GB | 125K | 46 | −0.4% ppl | Long context |
| Q5_K_M | 5.6 GB | 6.3 GB | 125K | 53 | −0.8% ppl | Long context |
| Q4_K_M | 4.8 GB | 5.5 GB | 125K | 62 | −1.9% ppl | Recommended |
| Q3_K_M | 3.9 GB | 4.5 GB | 125K | 76 | −5.4% ppl | Long context |
| Q2_K | 3.3 GB | 4.0 GB | 125K | 89 | −15% ppl | Long context |
Quality is the published perplexity delta against f16 weights. Max context assumes an f16 KV cache; q8_0 roughly doubles it. Only 6 of its 24 blocks keep a per-token KV cache; the rest are linear-attention, Mamba or convolution blocks with a fixed-size state.
How to run it
$ pip install mlx-lm $ mlx_lm.generate --model mlx-community/LFM2.5-8B-A1B-4bit \ --max-tokens 512 --prompt "Hello"
Apple's own array framework. The fastest path on Apple Silicon. More on MLX.
01Download is 4.8 GB. Keep it on an SSD — a first load off a spinning disk takes minutes.
02macOS caps what the GPU may wire down at about 24.0 GB of 32 GB. Raising it with iogpu.wired_limit_mb is possible, and risky.
03There is room to go to the model's full 125K context on this card.