Native
Transformers, vLLM, SGLang, or fine-tuning
Use the exact LiquidAI/LFM2.5-2.6B ID.
Liquid AI model record · Source checked August 5, 2026
Liquid AI publishes a 2.69B dense, text-only checkpoint with 131,072-token context and native tool calling. It ships in native, GGUF, MLX, and ONNX formats. That record supports local evaluation—not a promise that every phone, harness, task, or Flowith account is ready for it.
LiquidAI/LFM2.5-2.6B, post-trained for agentic workloads
2.69B-parameter dense, text-only LFM2.5 model
131,072 tokens in the official model card
Native weights, GGUF, MLX, and ONNX
Tool use, data extraction, RAG, and long-context workflows
Liquid AI does not recommend it for agentic coding or knowledge-heavy tasks
Not established by the provider release; verify the live workspace separately
Format decision
Transformers, vLLM, SGLang, or fine-tuning
Use the exact LiquidAI/LFM2.5-2.6B ID.
llama.cpp and compatible local applications
Choose a quantization only after measuring quality and memory.
Apple Silicon local inference
Measure unified-memory pressure with the intended context.
Cross-platform edge and hardware-accelerated deployment
Validate the exported graph and target execution provider.
Text, image and video models side by side. Compare them on the same prompt, pick one per shot, or let the agent choose.
Write it, picture it, film it. One sentence is enough to begin.