Yes — with 8.9 GB to spare
LFM2.5 8B-A1B at Q4_K_M fits your Radeon RX 7900 GRE entirely on the GPU at 8K context, at an estimated 159 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 | — | ~23 | Reference | 2.1 GB over |
| Q8_0 | 8.4 GB | 9.1 GB | 125K | 90 | −0.1% ppl | Long context |
| Q6_K | 6.5 GB | 7.2 GB | 125K | 117 | −0.4% ppl | Long context |
| Q5_K_M | 5.6 GB | 6.3 GB | 125K | 135 | −0.8% ppl | Long context |
| Q4_K_M | 4.8 GB | 5.5 GB | 125K | 159 | −1.9% ppl | Recommended |
| Q3_K_M | 3.9 GB | 4.5 GB | 125K | 196 | −5.4% ppl | Long context |
| Q2_K | 3.3 GB | 4.0 GB | 125K | 229 | −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 a Radeon RX 7900 GRE
| Model | Total | Tok/s est. | |
|---|---|---|---|
| LFM2.5 2.6B 2.7B · same family |
Q4_K_M · 2.2 GB | 230 | Runs great |
| Fara 7B 8.29B · similar size |
Q4_K_M · 5.7 GB | 75 | Runs great |
| Qwen3 8B 8.19B · similar size |
Q4_K_M · 6.3 GB | 76 | Runs great |
| Granite 4.1 8B 8.79B · similar size |
Q4_K_M · 6.8 GB | 71 | Runs great |
| Ministral 3 8B 8.92B · similar size |
Q4_K_M · 6.7 GB | 70 | Runs great |
| Llama 3.1 8B Instruct 8.03B · similar size |
Q4_K_M · 6.1 GB | 77 | Runs great |
| Gemma 4 E4B 8.0B · similar size |
Q4_K_M · 5.2 GB | 78 | 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 |