Model reference · open weights

LFM2.5

LFM2.5 is an open-weight language model from LiquidAI, listed in the AxForge catalogue. AxForge can bring it up on EU-owned hardware for you on request — with the licence handled where one is required.

Licence fee required LLMs LiquidAI 2 variants 856k downloads/mo
Request a licence + hosting quote All served models Not on the shared API today — deployed on request.

About

What LFM2.5 is

src="https://cdn-uploads.huggingface.co/production/uploads/61b8e2ba285851687028d395/2b08LKpev0DNEk6DlnWkY.png" alt="Liquid AI" style="width: 100%; max-width: 100%; height: auto; display: inline-block; margin-bottom: 0.5em; margin-top: 0.5em;" / LFM2.5-2.6B-GGUF LFM2.5 is a new family of hybrid models designed for on-device deployment. It builds on the LFM2 architecture with extended pre-training and reinforcement learning. Find more details in the original model card: https://huggingface.co/LiquidAI/LFM2.5-2.6B 🏃 How to run LFM2 Example usage with llama.cpp: QAD Q40 GGUF The Quantization-Aware Distillation (QAD) checkpoint is available as LFM2.5-2.6B-QAD-Q40.gguf. This is distinct from the post-training-quantized LFM2.5-2.6B-Q40.gguf; both use the GGUF Q40 format.

Summarised from the published model card. Read the full card on the HuggingFace links below.

Specifications

What it is

MakerLiquidAI
TypeLanguage models
Variants2
Runs withgguf
Based onLiquidAI/LFM2.5-2.6B
Released2026-08-01
Popularity856k downloads / month
Likes719
LicenceCommercial licence needed

How it works

How language models work

Your prompttext / messagesTransformerattention over tokensNext-token loopgenerate + streamResponsetext · tool callsA language model reads your tokens and predicts the next one, again and again, streaming the reply back.

Variants

Sizes & precisions

Open weights ship in several sizes and precisions. One page, all the variants — pick the one that fits your GPU. VRAM figures are estimates from model size.

VariantParamsPrecisionVRAMFits 16 GBWeights
LFM2.5-2.6B-GGUFGGUFWeights ↗
LFM2.5-2.6B2.7BBF16~6.2 GBWeights ↗

Using it via the API

Call it like any OpenAI endpoint

Once AxForge deploys lfm2-5 for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (lfm2-5 below is illustrative; you get the exact model name on deployment.)

$ curl -sS https://api.axforge.ai/v1/chat/completions \
  -H "Authorization: Bearer $AXFORGE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"lfm2-5","messages":[{"role":"user","content":"Hello"}]}'

Details

Languages, data & research

Languages

ar zh en fr de hi id it ja ko pl pt ru es

Tags

gguf liquid lfm2.5 llama.cpp text-generation ar zh en fr de hi id it ja

Papers

Licence

Commercial licence needed

The weights are open but its licence needs a commercial agreement for business use. AxForge can arrange that licence and host the model for you — you pay AxForge, we settle with the model’s maker. Ask us for a quote. Read the licence ↗

Sources

Weights & code

Want LFM2.5 on EU-owned hardware?

Request a licence + hosting quote See what’s served now

Explore

More language models

© 2026 AxForge · EU-hosted AI infrastructure Pricing Docs Trust Privacy Terms