Features
LFM2.5-1.2B-Instruct with best-in-class instruction following
LFM2.5-230M model for ultra-small edge devices
LFM2.5-VL-1.6B vision-language with multi-image comprehension
LFM2.5-VL-450M structured visual intelligence model
LFM2.5-Audio-1.5B native audio input/output with 8x faster detokenizer
LFM2.5-1.2B-JP Japanese-optimized chat model
LFM2.5-8B-A1B mixture-of-experts model (8B total, 1B active)
LFM2.5 Retrievers for fast multilingual search on edge
Open weights on Hugging Face and LEAP
Commercial use free under $10M annual revenue
Hybrid architecture for fast CPU inference with low memory
Reinforcement learning post-training pipeline
Supports fine-tuning for domain-specific assistants
Deployment via LEAP, llama.cpp, MLX, vLLM, ONNX
NPU optimization by AMD and Nexa AI
Unified API for 400+ models across 70+ providers
Automatic failover routing when a provider goes down
Model Fusion: combine budget models to rival frontier performance
Subagent delegation: frontier models hand off tasks to cheaper workers
Speech/transcription APIs (May 2026)
Unified Image API with capability discovery across 30+ models (June 2026)
OpenAI SDK compatible out of the box
Server-side presets to survive model deprecation
Edge-deployed for minimal latency
Budget controls and spend limits
Credit-based pricing with no subscriptions
Model routing visualization for latency and cost
Private model support for enterprise deployments
Data policy-based routing and enforcement
MCP server for coding agents (June 2026)
