NEWS · MODELS · #1919
LFM2.5-24B-A2B: 24B-parameter MoE agent model (2B active) for fast private on-device reasoning — open weights
LFM2.5-24B-A2B is a 24B-parameter MoE reasoning model that activates only 2B parameters per token, is reasoning‑only (emits explicit chains of thought), and is optimized for continuous, private agent use on-device. It expands context to 131K tokens, doubles vocabulary to 128K, reports high edge and GPU throughput (e.g., 184 tok/s on Apple M5 Max and >21K tok/s on an NVIDIA B300), is competitive with larger models on agentic and tool‑use benchmarks, and is available as open weights on Hugging Face with day‑one support in major inference runtimes (llama.cpp, MLX, vLLM, SGLang, ONNX).
KEY POINTS
- LFM2.5-24B-A2B is a 24B-parameter MoE reasoning model that activates only 2B parameters per token, is reasoning‑only (emits explicit chains of thought), and is optimized for continuous, private agent use on-device.
- It expands context to 131K tokens, doubles vocabulary to 128K, reports high edge and GPU throughput (e.g., 184 tok/s on Apple M5 Max and >21K tok/s on an NVIDIA B300), is competitive with larger models on agentic and tool‑use benchmarks, and is available as open weights on Hugging Face with day‑one support in major inference runtimes (llama.cpp, MLX, vLLM, SGLang, ONNX).
- Enables efficient, private, continuous agentic reasoning on local hardware by keeping active parameter cost low and shipping open weights and runtime support.
WHY IT MATTERS
Enables efficient, private, continuous agentic reasoning on local hardware by keeping active parameter cost low and shipping open weights and runtime support.