Skip to content

Liquid AI · Chat

LFM2.5-1.2B-Instruct

Liquid AI 🇺🇸ChatLiquidAI family
Max context
33K
Listings
1
Providers
1

Evidence and sources

🤗 LiquidAI/LFM2.5-1.2B-InstructReleased 6 Jan 2026Maker HQ: US (source)
Sources: FlowDot data, Hugging FacePrimary data from FlowDot from Hugging Face: release date

Input & output

as stated by the model's providers
Text
Text

Listings

 Flowdotliquid/lfm-2.5-1.2b-instruct:free · freeSource: FlowDot data33K$0.00$0.00

Benchmarks

No benchmark scores yet.

Around the web

  • Models — Liquid AI
    fastest, most compute-efficient, and capable foundation models so intelligence can live anywhere. Est. 2023 08.12.2026 …fastest, most compute-efficient, and capable foundation models so intelligence can live anywhere. Est. 2023 08.12.2026 Models 08.12.2026 Models LFM2.5-VL-3B: A Better and Faster Vision-Language Model…

    liquid.ai

  • LFM2.5-230M - Liquid Docs

    model.generate(**inputs, ${samplingParams}max_new_tokens=512) input_length = inputs["input_ids"].shape[1] response = tokenizer.decode(output[0][input_length:], skip_special_tokens=True) print(respons…

    docs.liquid.ai

  • LFM2.5-1.2B-Instruct - Liquid Docs

    model.generate(**inputs, ${samplingParams}max_new_tokens=512) input_length = inputs["input_ids"].shape[1] response = tokenizer.decode(output[0][input_length:], skip_special_tokens=True) print(respons…

    docs.liquid.ai

  • LFM2.5-230M: Built to Run Anywhere — Blog — Liquid AI
    For citations, please use the following reference or BibTeX: Liquid AI, "LFM2.5-230M: Built to Run …For citations, please use the following reference or BibTeX: Liquid AI, "LFM2.5-230M: Built to Run Anywhere", Liquid AI Blog, Jun 2026. @article{liquidAI2026230M, author = {Liquid AI}, title = {LFM2.…

    liquid.ai

  • LFM2.5-8B-A1B - Liquid Docs
    Specifications Property · Value Parameters · 8B (1.5B active) Context Length · 128K tokens Architecture …Specifications Property · Value Parameters · 8B (1.5B active) Context Length · 128K tokens Architecture · LFM2.5 (MoE) Extended context window for long documents and conversations 8B quality, 1.5B in…

    docs.liquid.ai

  • LFM2.5-VL-450M - Liquid Docs
    response = processor.batch_decode(outputs, skip_special_tokens=True)[0] print(response)} ; ← Back to Vision Models LFM2.5-VL-450M is Liquid AI's …response = processor.batch_decode(outputs, skip_special_tokens=True)[0] print(response)} ; ← Back to Vision Models LFM2.5-VL-450M is Liquid AI's smallest vision-language model, building on LFM2-VL-45…

    docs.liquid.ai

  • LFM2.5-1.2B-JP - Liquid Docs

    model.generate(**inputs, ${samplingParams}max_new_tokens=512) input_length = inputs["input_ids"].shape[1] response = tokenizer.decode(output[0][input_length:], skip_special_tokens=True) print(respons…

    docs.liquid.ai

  • LFM2.5-2.6B - Liquid Docs
    model directly from Hugging Face. For other installation methods and advanced usage, see the llama.cpp …model directly from Hugging Face. For other installation methods and advanced usage, see the llama.cpp guide . ; export const TextSglang = ({modelId, toolCallParser, samplingParams}) => Install: {uv …

    docs.liquid.ai

  • LFM2.5-Encoders: Fast at Long Context, Even on CPU — Blog — Liquid AI
    Liquid AI, "LFM2.5-Encoders: Fast at Long Context, Even on CPU", Liquid AI Blog, Jul 2026 …Liquid AI, "LFM2.5-Encoders: Fast at Long Context, Even on CPU", Liquid AI Blog, Jul 2026 @article{liquidAI2026Encoders, author = {Liquid AI}, title = {LFM2.5-Encoders: Fast at Long Context, Even on …

    liquid.ai

  • LFM2.5-VL-1.6B - Liquid Docs - Liquid Foundation Models
    response = processor.batch_decode(outputs, skip_special_tokens=True)[0] print(response)} ; ← Back to Vision Models LFM2.5-VL-1.6B is Liquid AI's …response = processor.batch_decode(outputs, skip_special_tokens=True)[0] print(response)} ; ← Back to Vision Models LFM2.5-VL-1.6B is Liquid AI's flagship vision-language model, delivering exceptional…

    docs.liquid.ai

Also known as: liquid/lfm-2.5-1.2b-instruct:free

Like this one. Tap or hover any dotted value, label or icon to see where it comes from and how it is measured. open details when tapped or hovered. How this data works