Post-Cutoff
Search For AI agents

Liquid AILFM3 familyCurrentLanguage modelReleased 27 Oct 2026

LFM3-1.7B

Run with a recent transformers (the vision, audio and omni siblings need 5.20–5.21 and trust_remote_code=True); see the model cards for llama.cpp and MLX builds.

Model idLiquidAI/LFM3-1.7B

PricePrice not published

Checked29 October 2026

No published training cutoff

At least365events since its release on 27 October 2026

6 historic, 69 major. 17 days of news.

Liquid AI doesn’t publish a training cutoff, so we count from its release date. The real gap is larger.

Five things it has never heard of

How to call it

2 ways to use LFM3-1.7B, with the model id each provider expects.

Providers, model ids, endpoints and docs for LFM3-1.7B
ProviderModel idEndpointDocs
Hugging Face (text model; also LFM3-1.7B-Base, GGUF and MLX builds) LiquidAI/LFM3-1.7B huggingface.co
Hugging Face (siblings on the same backbone) huggingface.co

Pricing

Price not published.

No price source linked. Checked 29 October 2026.

Specs

Input
Text
Output
Text
Context window
256,000 tokens
Max output
Not published
Open weights
Yes
Licence
lfm1.0
Training cutoff
Not published
Released
27 October 2026
Status
Current
Type
Language model

What stands out

What its maker marketed at launch, and what people found later, each with its source.

  • Small on-device agent model

    1.7B tri-hybrid model (13 gated short convolutions, 5 sliding-window and 6 global attention layers), ~1 GB at 4-bit, 256K context; Liquid reports WebArena-Verified 38.42 vs 3.02 for LFM2.5-2.6B and says it beats Qwen3.5-9B on long browser and business-app tasks (vendor numbers).

    Source: huggingface.co

  • One backbone for every modality

    Six 2B-class open models branch from LFM3-1.7B-Base: text, LFM3-VL-2B (first LFM with video input), LFM3-Audio-2B (18 languages, speech in and out), LFM3-Omni-2B (Liquid’s first omni model) and the d1-2B / d1-Omni-2B decision models.

    Source: huggingface.co

Notes

Released Oct 27, 2026 under the LFM Open License v1.0 (Hugging Face ‘lfm1.0’). Pre-trained on 22T tokens with 3.5T tokens of mid-training on agentic traces; post-trained for agent harnesses such as Hermes Agent, Pi and OpenClaw; fine-tunes on one GPU. Benchmarks are Liquid’s own.