Yes — with 40.9 GB to spare
LFM2.5 8B-A1B at Q4_K_M fits your L40S entirely on the GPU at 8K context, at an estimated 239 tokens per second. There is room for its full 125K window.
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.
The VRAM budget
Quantisation ladder
| Quant | Weights | Total @ 8K | Max context | Tok/s | Quality | Fit |
|---|---|---|---|---|---|---|
| F16 | 15.8 GB | 16.5 GB | 125K | 72 | Reference | Long context |
| Q8_0 | 8.4 GB | 9.1 GB | 125K | 136 | −0.1% ppl | Long context |
| Q6_K | 6.5 GB | 7.2 GB | 125K | 176 | −0.4% ppl | Long context |
| Q5_K_M | 5.6 GB | 6.3 GB | 125K | 203 | −0.8% ppl | Long context |
| Q4_K_M | 4.8 GB | 5.5 GB | 125K | 239 | −1.9% ppl | Recommended |
| Q3_K_M | 3.9 GB | 4.5 GB | 125K | 295 | −5.4% ppl | Long context |
| Q2_K | 3.3 GB | 4.0 GB | 125K | 344 | −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
$ ollama pull lfm2.5:8b $ OLLAMA_CONTEXT_LENGTH=8192 \ ollama run lfm2.5:8b
The default. One binary, a model registry, an OpenAI-compatible port. More on Ollama.
Related models on an L40S
| Model | Total | Tok/s est. | |
|---|---|---|---|
| LFM2.5 2.6B 2.7B · same family |
Q4_K_M · 2.2 GB | 345 | Runs great |
| Fara 7B 8.29B · similar size |
Q4_K_M · 5.7 GB | 112 | Runs great |
| Qwen3 8B 8.19B · similar size |
Q4_K_M · 6.3 GB | 114 | Runs great |
| Granite 4.1 8B 8.79B · similar size |
Q4_K_M · 6.8 GB | 106 | Runs great |
| Ministral 3 8B 8.92B · similar size |
Q4_K_M · 6.7 GB | 104 | Runs great |
| Llama 3.1 8B Instruct 8.03B · similar size |
Q4_K_M · 6.1 GB | 116 | Runs great |
| Gemma 4 E4B 8.0B · similar size |
Q4_K_M · 5.2 GB | 116 | Runs great |
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 |