All of our models share the following capabilities:
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.
- 32K token context length for extended conversations and document processing (128K for LFM2.5-8B-A1B)
- Designed for fast inference with Transformers, llama.cpp, vLLM, SGLang, MLX, Ollama, and LEAP
- Trainable via SFT, DPO, VLM, and GRPO workflows with LEAP Finetune, TRL, and Unsloth
Model Families
Text Models
Chat, tool calling, structured output, and classification.
Vision Models
Image understanding with LFM backbones and custom encoders.
Audio Models
Interleaved audio/text models for TTS, ASR, and voice chat.
Liquid Nanos
Task-specific models for extraction, summarization, RAG, and translation.
Common Workflows
GPU Serving
Use vLLM or SGLang for high-throughput serving, and Transformers for direct Python inference.
Fine-Tuning
Start with LEAP Finetune for managed workflows, or use TRL and Unsloth for framework-level control.
Model Repositories
Browse LiquidAI collections on Hugging Face for model weights, GGUF exports, MLX packages, ONNX exports, and model cards.
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, LM Studio, or Ollama. Append
-GGUFto any model name. - MLX — Best for Mac users with Apple Silicon. Leverages unified memory for fast inference via MLX. Browse at mlx-community.
- ONNX — Best for production deployments and edge devices. Cross-platform with ONNX Runtime across CPUs, GPUs, and accelerators. Append
-ONNXto 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, andF16.Q4_K_Moffers the best balance of size and quality. - MLX — Available in
3bit,4bit,5bit,6bit,8bit, andBF16.8bitis recommended. - ONNX — Supports
FP32,FP16,Q4, andQ8(MoE models also supportQ4F16).Q4is recommended for most deployments.