# LFM2-1.2B [Canonical model page](https://headlessthrones.com/models/liquid-ai-lfm2-1-2b) · [Model library](https://headlessthrones.com/models) Public catalog reference from Headless Thrones. Exact catalog ID: `liquid-ai-lfm2-1-2b`. Catalog source-check date: 2026-10-23. This brief contains the public catalog answers and any catalog guide, not private drafts, historical editorial revisions or independently measured rankings. The canonical HTML page may also display separately published editorial. Current catalog answers ## What to know about LFM2-1.2B AI-compiled from linked model documentation. This is a catalog reference, not an independent performance review. Catalog checked October 23, 2026. [Exact model](https://headlessthrones.com/models/liquid-ai-lfm2-1-2b#model-answer-identity) · [Access](https://headlessthrones.com/models/liquid-ai-lfm2-1-2b#model-answer-access) · [Inputs & outputs](https://headlessthrones.com/models/liquid-ai-lfm2-1-2b#model-answer-modalities) · [Weight details](https://headlessthrones.com/models/liquid-ai-lfm2-1-2b#model-answer-repository) ### Which LFM2-1.2B does this page describe? LFM2-1.2B is a model record from **Liquid AI** in the LFM2 family. [Source](https://huggingface.co/LiquidAI/LFM2-1.2B) The recorded model identifier or checkpoint is `LFM2-1.2B`. Use that exact identifier when checking documentation or a provider listing. [Source](https://huggingface.co/LiquidAI/LFM2-1.2B) ### How can you access LFM2-1.2B? The catalog documents **Open weights** access for LFM2-1.2B. [Source](https://huggingface.co/LiquidAI/LFM2-1.2B) As of the catalog check, this version was listed without confirmed general availability. [Source](https://huggingface.co/LiquidAI/LFM2-1.2B) Open weights means the model weights are distributed for use under their stated terms. It does not establish a hosted API, an open-source license, or a hardware requirement. ### What can LFM2-1.2B receive and generate? Documented inputs: **Text**. [Source](https://huggingface.co/LiquidAI/LFM2-1.2B) Documented outputs: **Text**. [Source](https://huggingface.co/LiquidAI/LFM2-1.2B) Input support and output generation are separate capabilities. Reading an image does not establish image generation; a text output listing does not establish speech output. File sizes, formats and media limits depend on the documented implementation. ### What is documented about the LFM2-1.2B checkpoint? This evidence refers to `LiquidAI/LFM2-1.2B` at recorded revision `40f3da0d0164913923aee9462c23077868b816a3`, checked October 23, 2026. [Repository metadata](https://huggingface.co/api/models/LiquidAI/LFM2-1.2B) Safetensors metadata records **1,170,340,608 stored parameters**. This is a stored-weight count, not necessarily the number activated per token, a download size or a GPU-memory requirement. [Repository metadata](https://huggingface.co/api/models/LiquidAI/LFM2-1.2B) Recorded architecture class: `Lfm2ForCausalLM`. [Repository metadata](https://huggingface.co/api/models/LiquidAI/LFM2-1.2B) Repository task tag: `text-generation`. A task tag identifies a distribution category; it does not measure performance on that task. [Repository metadata](https://huggingface.co/api/models/LiquidAI/LFM2-1.2B) Listed library: `transformers`. Check that library's version and model support before loading the weights. [Repository metadata](https://huggingface.co/api/models/LiquidAI/LFM2-1.2B) Repository language labels: en, ar, zh, fr, de, ja, ko, and es. These labels are not independent evaluations of language quality. [Repository metadata](https://huggingface.co/api/models/LiquidAI/LFM2-1.2B) Repository access gate: `false`. This records the repository's gate setting when checked; licensing and use terms still apply. [Repository metadata](https://huggingface.co/api/models/LiquidAI/LFM2-1.2B) #### What the configuration file says The pinned `config.json` contains these values. [Pinned configuration](https://huggingface.co/LiquidAI/LFM2-1.2B/resolve/40f3da0d0164913923aee9462c23077868b816a3/config.json) `max_position_embeddings`: 128,000 `torch_dtype`: bfloat16 `num_attention_heads`: 32 `num_key_value_heads`: 8 `num_hidden_layers`: 16 `hidden_size`: 2,048 Configuration values describe the checkpoint and its implementation. In particular, max\_position\_embeddings, sliding\_window and rope\_scaling do not independently establish an API context limit, tested usable length or hardware requirement. Runtime, quantization, cache, batch size and input length affect deployment behavior. Read the retrieved model card for setup and qualifications. [Model card](https://huggingface.co/LiquidAI/LFM2-1.2B/resolve/40f3da0d0164913923aee9462c23077868b816a3/README.md) **Catalog qualifications:** Official publisher inventory entry. Missing fields have not been verified. Repository timestamps are not release dates. [Source 1](https://huggingface.co/api/models/LiquidAI/LFM2-1.2B) · [Source 2](https://huggingface.co/LiquidAI/LFM2-1.2B/resolve/40f3da0d0164913923aee9462c23077868b816a3/README.md) · [Source 3](https://huggingface.co/LiquidAI/LFM2-1.2B/resolve/40f3da0d0164913923aee9462c23077868b816a3/config.json) **Evidence still missing here:** context or input capacity, knowledge and training-data cutoffs, and tested hardware requirements. Missing documentation is not evidence that a feature is unavailable. Headless Thrones has not independently benchmarked this model for this reference. Evaluate it on representative work before choosing it; these facts do not rank its accuracy, reliability, speed or suitability against another model. Keep the exact version in view ## Other LFM2 models from Liquid AI. These are separate records in the same publisher family. A shared family name does not establish equal capabilities or interchangeable licenses. ### [LFM2-1.2B-Extract](https://headlessthrones.com/models/liquid-ai-lfm2-1-2b-extract) Open weights ### [LFM2-1.2B-RAG](https://headlessthrones.com/models/liquid-ai-lfm2-1-2b-rag) Open weights ### [LFM2-1.2B-Tool](https://headlessthrones.com/models/liquid-ai-lfm2-1-2b-tool) Open weights ### [LFM2-2.6B](https://headlessthrones.com/models/liquid-ai-lfm2-2-6b) Open weights ### [LFM2-2.6B-Exp](https://headlessthrones.com/models/liquid-ai-lfm2-2-6b-exp) Open weights ### [LFM2-2.6B-Transcript](https://headlessthrones.com/models/liquid-ai-lfm2-2-6b-transcript) Open weights