Model reference · open weights
LFM2.5-VL is an open-weight language model from unsloth, 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.
About
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-VL-3B LFM2.5-VL-3B is a multimodal variant of LFM2.5, a family of hybrid models designed for on-device deployment. It builds on LFM2-VL-3B with further mid- and post-training. LFM2.5-VL-3B can process both text and images, and uses the LFM2.5-2.6B language model as its backbone, combined with a SigLIP2 NaFlex vision encoder. Better grounding: Improved grounding and object detection with natural language queries. Better OCR: Full page OCR with layout annotation. See layout annotation format for more information. Efficient inference: 228 tok/s on an Apple M5 Max and 116 tok/s on an AMD Ryzen AI Max+ 395, in under 3.3 GB of memory. Find more information about LFM2.5-VL-3B in our release post. [!NOTE] 💻 Demos: Try LFM2.5-VL-3B's vision understanding capabilities in a Hugging Face space without any setup: Vision-capable chat in your browser: allows you to upload images or use the webcam to capture images and let the model interact with them, as well as use tool calls and display generated bounding boxes. If you just want to chat about images, the LiquidAI playground is a fast way to do that. Model Details - LM Backbone: LFM2.5-2.6B - Vision encoder: SigLIP2 NaFlex shape‑optimized 400M - Vocabulary size: 128,000 - Context length: 32,768 tokens - Languages: English, Arabic, Chinese, French, German, Italian, Japanese, Korean, Portuguese, Spanish, Vietnamese, Thai, Indonesian, Hindi, Russian, Polish - Native resolution processing: Uses SigLIP2's NaFlex; large images are split into non-overlapping 512×512 patches and a resized whole-image thumbnail. - Generation parameters: - text: temperature=0.2, topk=50, repetitionpenalty=1.0 - vision: Use the processorconfig.json file. We recommend using it for single-turn, high-throughput, low-latency tasks; for example, for near-realtime object detection in automotive applications, batch processing scanned documents with OCR with layout information for turning PDFs into searchable text
Summarised from the published model card. Read the full card on the HuggingFace links below.
Specifications
| Maker | unsloth |
|---|---|
| Type | Language models |
| Variants | 2 |
| Runs with | transformers |
| Based on | LiquidAI/LFM2.5-VL-3B |
| Released | 2026-08-12 |
| Popularity | 14k downloads / month |
| Likes | 16 |
| Licence | Commercial licence needed |
How it works
Variants
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.
Using it via the API
Once AxForge deploys lfm2-5-vl for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (lfm2-5-vl 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-vl","messages":[{"role":"user","content":"Hello"}]}'
Licence
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 ↗