LFM2.5 2.6B — VRAM, speed & local setup
Written by Jakub Rusinowski · Last updated
Liquid AI's on-device agentic model: 2.69B parameters over 30 layers, of which only 8 are attention — the other 22 are double-gated short convolutions that cache nothing. That is why its KV cache stays small at a 128K context where a conventional 2.7B model's would not. Trained on 34T tokens, post-trained for tool calling.
LFM2.5 2.6B needs about 2 GB of VRAM at Q4_K_M — quantized weights plus framework overhead, before any KV cache. On Apple Silicon that figure comes out of unified memory.
VRAM and speed by quantization
Quoted against NVIDIA RTX 4090 (24 GB). Weights plus overhead only: this model's architecture is unpublished, so no KV cache is added.
| Quant | Memory | VRAM | Speed (est.) | Fit |
|---|---|---|---|---|
| Q2_K 2.63 bpw | 1.7 GB | ~253 tok/s | Fits | |
| Q3_K_M 3.41 bpw | 1.9 GB | ~233 tok/s | Fits | |
| Q4_K_M 4.83 bpw | 2.4 GB | ~203 tok/s | Fits | |
| Q5_K_M 5.67 bpw | 2.7 GB | ~189 tok/s | Fits | |
| Q6_K 6.56 bpw | 3 GB | ~176 tok/s | Fits | |
| Q8_0 8.50 bpw | 3.7 GB | ~152 tok/s | Fits | |
| F16 16.00 bpw | 6.2 GB | ~101 tok/s | Fits |
Black marker = usable memory on the NVIDIA RTX 4090 (24 GB). Estimates from the memory-bandwidth roofline on the methodology page. LFM2.5 2.6B VRAM calculator →
Get LFM2.5 2.6B running
The cheapest catalogued GPU that runs LFM2.5 2.6B is the Intel Arc B570 (10 GB).
or compare on Vast.ai from $0.35/hr (typical low · varies)
As an Amazon Associate we earn from qualifying purchases. Cloud GPU links are referral links — we may earn a commission at no extra cost to you.
How to run LFM2.5 2.6B
Install Ollama, then run:
ollama run lfm2-5Specifications
Corroborated — Two or more independent sources agree on these figures, but the model card itself was not retrieved. Treat the numbers as good rather than confirmed.
- Parameters
- 2.69 Billion
- Context window
- 131,072
- Architecture
- Hybrid (22 conv + 8 GQA)
- Provider
- Liquid AI
- Licence
- LFM Open License v1.0
- Practical deployment
- Edge device (phone, SBC)
- Specified at
- Q4_K_M
- System RAM
- 8 GB
- Record updated
- 2026-09-19
Weights are downloadable and commercial use is permitted, subject to the licence’s acceptable-use terms.
Commercial use is licensed only below $10M annual revenue; above that, a separate agreement.
See also LFM3 1.7B
Quality and use cases
Scores as published by the model’s authors or an independent evaluator — quality, not throughput, and not measured by us.
Can I run LFM2.5 2.6B on my GPU?
- LFM2.5 on AMD Radeon RX 9060 XT 8GB
- LFM2.5 on Intel Arc B570
- LFM2.5 on Intel Arc B580
- LFM2.5 on NVIDIA GeForce RTX 3060 (12GB)
- LFM2.5 on NVIDIA GeForce RTX 3070
- LFM2.5 on NVIDIA GeForce RTX 3070 Ti
- LFM2.5 on NVIDIA GeForce RTX 3080 (10GB)
- LFM2.5 on NVIDIA GeForce RTX 4060
- LFM2.5 on NVIDIA GeForce RTX 4070
- LFM2.5 on NVIDIA GeForce RTX 4070 Super
- LFM2.5 on NVIDIA GeForce RTX 4070 Ti
- LFM2.5 on NVIDIA GeForce RTX 5060
- LFM2.5 on NVIDIA GeForce RTX 5060 Ti 8GB
- LFM2.5 on NVIDIA GeForce RTX 5070
Other LFM2.5 sizes
LFM2.5 2.6B — frequently asked questions
How much VRAM does LFM2.5 2.6B need?
About 2 GB at Q4_K_M — quantized weights plus framework overhead, before any KV cache. The cache grows with context length and is added on top; the table above folds it in. Apple Silicon counts unified memory toward the same figure.
Does LFM2.5 2.6B run on an RTX 4090 (24 GB)?
Yes. LFM2.5 2.6B needs about 2 GB at Q4_K_M, inside a 24 GB card, at an estimated 203 tokens/sec.
How do I run LFM2.5 2.6B locally?
Install Ollama and run `ollama run lfm2-5`. That pulls the weights and starts a local OpenAI-compatible endpoint; after the download nothing leaves the machine.
What other sizes does LFM2.5 come in?
LFM2.5 2.6B (2 GB), LFM2.5-8B-A1B (6 GB), LFM2.5-24B-A2B (15 GB). Every size shares the family's training and licence; the larger ones score higher and need proportionally more memory.