No — not on this device
LFM2.5 8B-A1B at Q4_K_M needs 5.5 GB against 5.4 GB usable, and the shortfall of 0.1 GB is more than 64 GB of system RAM can cover at a tolerable speed. A smaller sibling or a lower quantisation is the honest answer here.
An 8B MoE with ~1.5B active, aimed at laptops without a GPU. Licence is permissive below $10M revenue.
Hardware requirements What hardware do I need to run LFM2.5 8B-A1B? →At Q4_K_M with an 8K context: a 8 GB GPU (RTX 4060 Laptop) or a 16 GB Mac (M4). Minimum, recommended, high-quality and long-context tiers, with all 114 devices checked at every quantisation.
Fits instead: LFM2.5 2.6B (2.2 GB)
The VRAM budget
Quantisation ladder
| Quant | Weights | Total @ 8K | Max context | Tok/s | Quality | Fit |
|---|---|---|---|---|---|---|
| F16 | 15.8 GB | 16.5 GB | — | ~6.3 | Reference | 11.1 GB over |
| Q8_0 | 8.4 GB | 9.1 GB | — | ~12 | −0.1% ppl | 3.7 GB over |
| Q6_K | 6.5 GB | 7.2 GB | — | ~15 | −0.4% ppl | 1.8 GB over |
| Q5_K_M | 5.6 GB | 6.3 GB | — | ~18 | −0.8% ppl | 0.9 GB over |
| Q4_K_M | 4.8 GB | 5.5 GB | 3K | ~21 | −1.9% ppl | 0.1 GB over |
| Q3_K_M | 3.9 GB | 4.5 GB | 80K | 26 | −5.4% ppl | Long context |
| Q2_K | 3.3 GB | 4.0 GB | 125K | 30 | −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.
Related models on an M1 · 8 GB
| Model | Total | Tok/s est. | |
|---|---|---|---|
| LFM2.5 2.6B 2.7B · same family |
Q4_K_M · 2.2 GB | 25 | Runs great |
| Fara 7B 8.29B · similar size |
Q4_K_M · 5.7 GB | — | Won't fit |
| Qwen3 8B 8.19B · similar size |
Q4_K_M · 6.3 GB | — | Won't fit |
| Granite 4.1 8B 8.79B · similar size |
Q4_K_M · 6.8 GB | — | Won't fit |
| Ministral 3 8B 8.92B · similar size |
Q4_K_M · 6.7 GB | — | Won't fit |
| Llama 3.1 8B Instruct 8.03B · similar size |
Q4_K_M · 6.1 GB | — | Won't fit |
| Gemma 4 E4B 8.0B · similar size |
Q4_K_M · 5.2 GB | 8.4 | Tight fit |
LFM2.5 8B-A1B on other hardware
| Device | Total | Tok/s est. | |
|---|---|---|---|
| GeForce RTX 4060 Laptop 7.0 GB usable · 256 GB/s |
5.5 GB | 71 | Runs great |
| GeForce RTX 3060 12 GB 10.6 GB usable · 360 GB/s |
5.5 GB | 99 | Runs great |
| M4 · 16 GB 10.7 GB usable · 120 GB/s |
5.5 GB | 37 | Runs great |
| GeForce RTX 4090 22.4 GB usable · 1008 GB/s |
5.5 GB | 278 | Runs great |
| Radeon RX 7900 XTX 22.4 GB usable · 960 GB/s |
5.5 GB | 265 | Runs great |
| M3 Max · 64 GB 48.0 GB usable · 400 GB/s |
5.5 GB | 124 | Runs great |