> ## Documentation Index
> Fetch the complete documentation index at: https://liquidai-ovenmitt-fix-models--decision-models-matrix-row.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Liquid Foundation Models

> Liquid Foundation Models (LFMs) are a new class of multimodal architectures built for fast inference and on-device deployment. Browse all available models and formats here.

<div className="capabilities">
  All of our models share the following capabilities:

  * 32K token context length for extended conversations and document processing (128K for LFM2.5-8B-A1B)
  * Designed for fast inference with [Transformers](/deployment/gpu-inference/transformers), [llama.cpp](/deployment/on-device/llama-cpp), [vLLM](/deployment/gpu-inference/vllm), [SGLang](/deployment/gpu-inference/sglang), [MLX](/deployment/on-device/mlx), [Ollama](/deployment/on-device/ollama), and [Atomic Chat](/deployment/on-device/atomic-chat)
  * Trainable via SFT, DPO, VLM, and GRPO workflows with [LEAP Finetune](/lfm/fine-tuning/leap-finetune), [TRL](/lfm/fine-tuning/trl), and [Unsloth](/lfm/fine-tuning/unsloth)
</div>

<Panel>
  * [Liquid Playground](https://playground.liquid.ai/chat?model=cmk0wefde000204jp2knb2qr8)
  * [HuggingFace Collections](https://huggingface.co/LiquidAI/collections)
  * [LEAP Finetune](https://github.com/Liquid4All/leap-finetune)
  * [OpenRouter API](https://openrouter.ai/liquid)
</Panel>

Start with the model family that matches your input and output shape, then choose a runtime based on where you want to run it. Use the complete matrix below when you need exact repository and format availability.

## Model Families

<CardGroup cols={2}>
  <Card title="Text Models" icon="comment" href="/lfm/models/text-models">
    Chat, tool calling, structured output, and classification.
  </Card>

  <Card title="Vision Models" icon="eye" href="/lfm/models/vision-models">
    Image understanding with LFM backbones and custom encoders.
  </Card>

  <Card title="Audio Models" icon="headphones" href="/lfm/models/audio-models">
    Interleaved audio/text models for TTS, ASR, and voice chat.
  </Card>

  <Card title="Decision Models" icon="scale-balanced" href="/lfm/models/decision-models">
    Purpose-built models for classification, routing, and scoring.
  </Card>

  <Card title="Liquid Nanos" icon="sparkles" href="/lfm/models/liquid-nanos">
    Task-specific models for extraction, summarization, RAG, and translation.
  </Card>
</CardGroup>

## Common Workflows

<CardGroup cols={2}>
  <Card title="GPU Serving" icon="server" href="/deployment/gpu-inference/vllm">
    Use [vLLM](/deployment/gpu-inference/vllm) or [SGLang](/deployment/gpu-inference/sglang) for high-throughput serving, and [Transformers](/deployment/gpu-inference/transformers) for direct Python inference.
  </Card>

  <Card title="Local and On-Device" icon="laptop" href="/deployment/on-device/llama-cpp">
    Use [llama.cpp](/deployment/on-device/llama-cpp), [Ollama](/deployment/on-device/ollama), [Atomic Chat](/deployment/on-device/atomic-chat), or [MLX](/deployment/on-device/mlx) depending on platform and packaging needs. To embed a model in an iOS, Android, or desktop app, see [Build with llama.cpp](/deployment/on-device/llama-cpp/mobile).
  </Card>

  <Card title="Fine-Tuning" icon="sliders" href="/lfm/fine-tuning/leap-finetune">
    Start with [LEAP Finetune](/lfm/fine-tuning/leap-finetune) for managed workflows, or use [TRL](/lfm/fine-tuning/trl) and [Unsloth](/lfm/fine-tuning/unsloth) for framework-level control.
  </Card>

  <Card title="Model Repositories" icon="database" href="https://huggingface.co/LiquidAI/collections">
    Browse LiquidAI collections on Hugging Face for model weights, GGUF exports, MLX packages, ONNX exports, and model cards.
  </Card>
</CardGroup>

## Formats

Use the format that matches your runtime and deployment target:

* **GGUF** — Best for local CPU/GPU inference on any platform. Use with [llama.cpp](/deployment/on-device/llama-cpp), [LM Studio](/deployment/on-device/lm-studio), [Ollama](/deployment/on-device/ollama), or [Atomic Chat](/deployment/on-device/atomic-chat). Append `-GGUF` to any model name.
* **MLX** — Best for Mac users with Apple Silicon. Leverages unified memory for fast inference via [MLX](/deployment/on-device/mlx) or [Atomic Chat](/deployment/on-device/atomic-chat). Browse at [mlx-community](https://huggingface.co/mlx-community/collections?search=LFM).
* **ONNX** — Best for production deployments and edge devices. Cross-platform with ONNX Runtime across CPUs, GPUs, and accelerators. Append `-ONNX` to any model name.

### Quantization

Quantization reduces model size and speeds up inference with minimal quality loss. Available options by format:

* **GGUF** — Supports `Q4_0`, `Q4_K_M`, `Q5_K_M`, `Q6_K`, `Q8_0`, `BF16`, and `F16`. `Q4_K_M` offers the best balance of size and quality.
* **MLX** — Available in `3bit`, `4bit`, `5bit`, `6bit`, `8bit`, and `BF16`. `8bit` is recommended.
* **ONNX** — Supports `FP32`, `FP16`, `Q4`, and `Q8` (MoE models also support `Q4F16`). `Q4` is recommended for most deployments.

## Complete Model Matrix

| Model | Family | HF | GGUF | MLX | ONNX | Trainable? |
| - | - | - | - | - | - | - |
| **Text-to-text Models** | | | | | | |
| [LFM2.5-1.2B-Instruct](/lfm/models/lfm25-1.2b-instruct) | LFM2.5 (Latest release) | [✓](https://huggingface.co/LiquidAI/LFM2.5-1.2B-Instruct) | [✓](https://huggingface.co/LiquidAI/LFM2.5-1.2B-Instruct-GGUF) | [✓](https://huggingface.co/LiquidAI/LFM2.5-1.2B-Instruct-MLX-8bit) | [✓](https://huggingface.co/LiquidAI/LFM2.5-1.2B-Instruct-ONNX) | Yes (TRL) |
| [LFM2.5-1.2B-Thinking](/lfm/models/lfm25-1.2b-thinking) | LFM2.5 (Latest release) | [✓](https://huggingface.co/LiquidAI/LFM2.5-1.2B-Thinking) | [✓](https://huggingface.co/LiquidAI/LFM2.5-1.2B-Thinking-GGUF) | [✓](https://huggingface.co/LiquidAI/LFM2.5-1.2B-Thinking-MLX-8bit) | [✓](https://huggingface.co/LiquidAI/LFM2.5-1.2B-Thinking-ONNX) | Yes (TRL) |
| [LFM2.5-1.2B-JP](/lfm/models/lfm25-1.2b-jp) | LFM2.5 (Latest release) | [✓](https://huggingface.co/LiquidAI/LFM2.5-1.2B-JP) | [✓](https://huggingface.co/LiquidAI/LFM2.5-1.2B-JP-GGUF) | [✓](https://huggingface.co/LiquidAI/LFM2.5-1.2B-JP-MLX-8bit) | [✓](https://huggingface.co/LiquidAI/LFM2.5-1.2B-JP-ONNX) | Yes (TRL) |
| [LFM2.5-350M](/lfm/models/lfm25-350m) | LFM2.5 (Latest release) | [✓](https://huggingface.co/LiquidAI/LFM2.5-350M) | [✓](https://huggingface.co/LiquidAI/LFM2.5-350M-GGUF) | [✓](https://huggingface.co/LiquidAI/LFM2.5-350M-MLX-8bit) | [✓](https://huggingface.co/LiquidAI/LFM2.5-350M-ONNX) | Yes (TRL) |
| [LFM2.5-230M](/lfm/models/lfm25-230m) | LFM2.5 (Latest release) | [✓](https://huggingface.co/LiquidAI/LFM2.5-230M) | [✓](https://huggingface.co/LiquidAI/LFM2.5-230M-GGUF) | [✓](https://huggingface.co/LiquidAI/LFM2.5-230M-MLX-8bit) | [✓](https://huggingface.co/LiquidAI/LFM2.5-230M-ONNX) | Yes (TRL) |
| [LFM2.5-2.6B](/lfm/models/lfm25-2.6b) | LFM2.5 (Latest release) | [✓](https://huggingface.co/LiquidAI/LFM2.5-2.6B) | [✓](https://huggingface.co/LiquidAI/LFM2.5-2.6B-GGUF) | [✓](https://huggingface.co/LiquidAI/LFM2.5-2.6B-MLX) | [✓](https://huggingface.co/LiquidAI/LFM2.5-2.6B-ONNX) | Yes (TRL) |
| [LFM2.5-8B-A1B](/lfm/models/lfm25-8b-a1b) | LFM2.5 (Latest release) | [✓](https://huggingface.co/LiquidAI/LFM2.5-8B-A1B) | [✓](https://huggingface.co/LiquidAI/LFM2.5-8B-A1B-GGUF) | [✓](https://huggingface.co/LiquidAI/LFM2.5-8B-A1B-MLX-8bit) | [✓](https://huggingface.co/LiquidAI/LFM2.5-8B-A1B-ONNX) | Yes (TRL) |
| [LFM2-24B-A2B](/lfm/models/lfm2-24b-a2b) | LFM2 | [✓](https://huggingface.co/LiquidAI/LFM2-24B-A2B) | [✓](https://huggingface.co/LiquidAI/LFM2-24B-A2B-GGUF) | [✓](https://huggingface.co/LiquidAI/LFM2-24B-A2B-MLX-8bit) | [✓](https://huggingface.co/LiquidAI/LFM2-24B-A2B-ONNX) | Yes (TRL) |
| [LFM2-700M](/lfm/models/lfm2-700m) | LFM2 | [✓](https://huggingface.co/LiquidAI/LFM2-700M) | [✓](https://huggingface.co/LiquidAI/LFM2-700M-GGUF) | [✓](https://huggingface.co/mlx-community/LFM2-700M-8bit) | [✓](https://huggingface.co/onnx-community/LFM2-700M-ONNX) | Yes (TRL) |
| **Vision Language Models** | | | | | | |
| [LFM2.5-VL-3B](/lfm/models/lfm25-vl-3b) | LFM2.5 (Latest release) | [✓](https://huggingface.co/LiquidAI/LFM2.5-VL-3B) | [✓](https://huggingface.co/LiquidAI/LFM2.5-VL-3B-GGUF) | [✓](https://huggingface.co/LiquidAI/LFM2.5-VL-3B-MLX-8bit) | [✓](https://huggingface.co/LiquidAI/LFM2.5-VL-3B-ONNX) | Yes (TRL) |
| [LFM2.5-VL-1.6B](/lfm/models/lfm25-vl-1.6b) | LFM2.5 (Latest release) | [✓](https://huggingface.co/LiquidAI/LFM2.5-VL-1.6B) | [✓](https://huggingface.co/LiquidAI/LFM2.5-VL-1.6B-GGUF) | [✓](https://huggingface.co/mlx-community/LFM2.5-VL-1.6B-8bit) | [✓](https://huggingface.co/LiquidAI/LFM2.5-VL-1.6B-ONNX) | Yes (TRL) |
| [LFM2.5-VL-450M](/lfm/models/lfm25-vl-450m) | LFM2.5 (Latest release) | [✓](https://huggingface.co/LiquidAI/LFM2.5-VL-450M) | [✓](https://huggingface.co/LiquidAI/LFM2.5-VL-450M-GGUF) | ✗ | [✓](https://huggingface.co/LiquidAI/LFM2.5-VL-450M-ONNX) | Yes (TRL) |
| **Audio Models** | | | | | | |
| [LFM2.5-Audio-1.5B](/lfm/models/lfm25-audio-1.5b) | LFM2.5 (Latest release) | [✓](https://huggingface.co/LiquidAI/LFM2.5-Audio-1.5B) | [✓](https://huggingface.co/LiquidAI/LFM2.5-Audio-1.5B-GGUF) | ✗ | [✓](https://huggingface.co/LiquidAI/LFM2.5-Audio-1.5B-ONNX) | Yes (TRL) |
| [LFM2.5-Audio-1.5B-JP](/lfm/models/lfm25-audio-1.5b-jp) | LFM2.5 (Latest release) | [✓](https://huggingface.co/LiquidAI/LFM2.5-Audio-1.5B-JP) | [✓](https://huggingface.co/LiquidAI/LFM2.5-Audio-1.5B-JP-GGUF) | ✗ | ✗ | Yes (TRL) |
| [LFM2-Audio-1.5B](/lfm/models/lfm2-audio-1.5b) | LFM2 | [✓](https://huggingface.co/LiquidAI/LFM2-Audio-1.5B) | [✓](https://huggingface.co/LiquidAI/LFM2-Audio-1.5B-GGUF) | ✗ | ✗ | No |
| **Decision Models** | | | | | | |
| [d1](/lfm/models/decision-models) | d1 | API | — | — | — | No |
| **Liquid Nanos** | | | | | | |
| [LFM2.5-VL-1.6B-Extract](/lfm/models/lfm25-vl-1.6b-extract) | LFM2.5 (Latest release) | [✓](https://huggingface.co/LiquidAI/LFM2.5-VL-1.6B-Extract) | [✓](https://huggingface.co/LiquidAI/LFM2.5-VL-1.6B-Extract-GGUF) | ✗ | ✗ | Yes (TRL) |
| [LFM2.5-VL-450M-Extract](/lfm/models/lfm25-vl-450m-extract) | LFM2.5 (Latest release) | [✓](https://huggingface.co/LiquidAI/LFM2.5-VL-450M-Extract) | [✓](https://huggingface.co/LiquidAI/LFM2.5-VL-450M-Extract-GGUF) | ✗ | ✗ | Yes (TRL) |
| [LFM2.5-Embedding-350M](/lfm/models/lfm25-embedding-350m) | LFM2.5 (Latest release) | [✓](https://huggingface.co/LiquidAI/LFM2.5-Embedding-350M) | [✓](https://huggingface.co/LiquidAI/LFM2.5-Embedding-350M-GGUF) | ✗ | ✗ | Yes (sentence-transformers) |
| [LFM2.5-ColBERT-350M](/lfm/models/lfm25-colbert-350m) | LFM2.5 (Latest release) | [✓](https://huggingface.co/LiquidAI/LFM2.5-ColBERT-350M) | [✓](https://huggingface.co/LiquidAI/LFM2.5-ColBERT-350M-GGUF) | ✗ | ✗ | Yes (PyLate) |
| [LFM2.5-Encoder-350M](/lfm/models/lfm25-encoder-350m) | LFM2.5 (Latest release) | [✓](https://huggingface.co/LiquidAI/LFM2.5-Encoder-350M) | ✗ | ✗ | ✗ | Yes (Transformers) |
| [LFM2.5-Encoder-230M](/lfm/models/lfm25-encoder-230m) | LFM2.5 (Latest release) | [✓](https://huggingface.co/LiquidAI/LFM2.5-Encoder-230M) | ✗ | ✗ | ✗ | Yes (Transformers) |
| [LFM2-350M-ENJP-MT](/lfm/models/lfm2-350m-enjp-mt) | LFM2 | [✓](https://huggingface.co/LiquidAI/LFM2-350M-ENJP-MT) | [✓](https://huggingface.co/LiquidAI/LFM2-350M-ENJP-MT-GGUF) | [✓](https://huggingface.co/mlx-community/LFM2-350M-ENJP-MT-8bit) | [✓](https://huggingface.co/onnx-community/LFM2-350M-ENJP-MT-ONNX) | Yes (TRL) |
| [LFM2-350M-Math](/lfm/models/lfm2-350m-math) | LFM2 | [✓](https://huggingface.co/LiquidAI/LFM2-350M-Math) | [✓](https://huggingface.co/LiquidAI/LFM2-350M-Math-GGUF) | ✗ | [✓](https://huggingface.co/onnx-community/LFM2-350M-Math-ONNX) | Yes (TRL) |
| [LFM2-350M-PII-Extract-JP](/lfm/models/lfm2-350m-pii-extract-jp) | LFM2 | [✓](https://huggingface.co/LiquidAI/LFM2-350M-PII-Extract-JP) | [✓](https://huggingface.co/LiquidAI/LFM2-350M-PII-Extract-JP-GGUF) | ✗ | ✗ | Yes (TRL) |
| [LFM2-2.6B-Transcript](/lfm/models/lfm2-2.6b-transcript) | LFM2 | [✓](https://huggingface.co/LiquidAI/LFM2-2.6B-Transcript) | [✓](https://huggingface.co/LiquidAI/LFM2-2.6B-Transcript-GGUF) | ✗ | [✓](https://huggingface.co/onnx-community/LFM2-2.6B-Transcript-ONNX) | Yes (TRL) |

<Note>Looking for an older model? Deprecated models and their recommended replacements are listed on the [Deprecations](/lfm/help/deprecations) page.</Note>


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.