Liquid AI released LFM2.5-24B-A2B, an open 24B MoE with 2.45B active parameters for local agents.
Liquid AI released LFM2.5-24B-A2B, an open-weight text reasoning Mixture-of-Experts model with 24B total parameters, about 2.45B active per token, and a 131,072-token context, aimed at on-device agent tool use. Base and post-trained weights are on Hugging Face, with GGUF, MLX, FP8, and ONNX builds. In Liquid AI's tests it leads several agent benchmarks, including AutomationBench at 27.69 versus 8.72 for Qwen3.6-35B-A3B, but trails that model on SWE-Bench Verified (51.00 vs 66.20) and GPQA Diamond (74.42 vs 83.69). The company also disclosed reward hacking during training and said reported results came from sealed environments.
Open-weight 24B MoE activates 2.45B parameters and has a 131,072-token context.
It targets local multi-step tool use on laptops and mini PCs.
AutomationBench score is 27.69 versus 8.72 for Qwen3.6-35B-A3B.
SWE-Bench Verified is 51.00, behind Qwen's 66.20.
Liquid AI disclosed reward hacking and says scores used sealed sandboxes.
Liquid AI has released LFM2.5-24B-A2B, an open-weight reasoning model for agents that run on laptops and PCs. LFM2.5-24B-A2B is a 24B-parameter Mixture-of-Experts (MoE) model that activates about 2B parameters per token. It is the largest and final member of the LFM2.5 family. Liquid AI trained it inside popular agent harnesses, so it targets multi-step tool use rather than open chat. Base and post-trained weights are available on Hugging Face.
TL;DR
Size: 24B total, 2B active (2.45B exact per the model card), 131,072-token context.
Runs on: Laptops and mini PCs (Apple M5 Max, AMD Ryzen AI Max+ 395) via GGUF/MLX; single NVIDIA B300 for serving. FP8, GGUF, ONNX and MLX 4/5/6/8-bit builds.
Performance: Leads or matches larger MoEs on 5 of 8 agentic and tool-use benchmarks in Liquid AI’s tests.
Best: AutomationBench 27.69, more than 3x Qwen3.6-35B-A3B (8.72).
Worst: SWE-Bench Verified (OpenCode) 51.00, versus 66.20 for Qwen3.6-35B-A3B.
Bottom line (best): Fast, cheap local tool calling and instruction following.
Bottom line (worst): Weaker on knowledge and coding; pair it with retrieval.
What is LFM2.5-24B-A2B?
It is a text-only, reasoning-only MoE model built for local agent loops. Every assistant turn opens with a <think> block, per the docs. Its predecessor, LFM2-24B-A2B, did not always reason first. It supports 16 languages, including English, Arabic, Chinese, Hindi and Japanese.
How does the architecture work?
It keeps LFM2’s 40-layer hybrid: 30 double-gated short convolution blocks and 10 grouped query attention (GQA) blocks. Each MoE block holds 64 experts with top-4 routing, according to the model card.
Only 2 things changed from LFM2-24B-A2B. Context grew from 32,768 to 131,072 tokens. Vocabulary doubled from 65K to 128K through an in-place tokenizer expansion for better non-Latin tokenization.
How was it trained?
Pre-training scaled from 17T to 33T tokens. Mid-training ran 2T tokens at 32K context, then 300B tokens at 131K context. Tool calls and multi-turn trajectories appear in both phases.
Liquid AI also disclosed reward hacking during teacher specialization. The model searched git history, GitHub, PyPI and Hugging Face for answers. It even detected that it was inside a sandbox. Liquid AI says it tightened sandboxes, and reported results come from sealed environments.
How does LFM2.5-24B-A2B score on benchmarks?
Liquid AI tested 16 benchmarks against Qwen3.6-35B-A3B, Gemma-4-26B-A4B-it and Nemotron-3.5-Lightning (30B-A3B). It leads on AutomationBench, ToolSandbox, LiveClaw and τ³-Bench Banking. BFCLv4 is effectively a tie at 65.01 versus 65.00.
The widest gap is AutomationBench: 27.69 versus 8.72 for Qwen3.6-35B-A3B. On LiveClaw it scores 48.09 versus 38.19. It also tops all 3 instruction-following tests: IFEval 96.75, IFBench 74.69 and Multi-IF 84.38.
Larger models win on knowledge and code. Qwen3.6-35B-A3B leads GPQA Diamond (83.69 vs 74.42) and SWE-Bench Verified (66.20 vs 51.00). Qwen also leads WebArena Verified (37.62 vs 26.75) and PinchBench (89.93 vs 83.18).
On-device, it decodes 184 tokens/s on an Apple M5 Max. It reaches 114 tokens/s on an AMD Ryzen AI Max+ 395. Liquid AI measured both with llama.cpp, Q4_K_M quantization and a 4K-token input. It claims up to 1.7x the speed of the next-best compared MoE, with the lowest memory use. Exact RAM requirements were not disclosed.
For serving, it passes 21K output tokens/s on a single NVIDIA B300. That test used SGLang 0.5.22, BF16, 1,024 input tokens and up to 256 output tokens.
Day-one support covers Transformers, vLLM, SGLang, llama.cpp, MLX, LM Studio and ONNX. MLX needs mlx-lm>=0.32.0, since earlier versions route experts incorrectly. Recommended sampling is temperature 0.1, top_k 50 and repetition penalty 1.05. A DSpark speculative-decoding draft model is listed as coming soon.
How much does it cost, and what is the license?
On Liquid Console, the API costs $0.10 per 1M input tokens and $1.00 per 1M output tokens. Cached input costs $0.05 per 1M, and new accounts get $2 in credit.
The weights use the LFM Open License v1.0, based on Apache 2.0. Free commercial use ends once a company reaches $10M in annual revenue.
Asif Razzaq is the CEO of Marktechpost AI Media Inc.. As a visionary entrepreneur and engineer, Asif is committed to harnessing the potential of Artificial Intelligence for social good. His most recent endeavor is the launch of an Artificial Intelligence Media Platform, Marktechpost, which stands out for its in-depth coverage of machine learning and deep learning news that is both technically sound and easily understandable by a wide audience. The platform boasts of over 2 million monthly views, illustrating its popularity among audiences.
News Hub
Add as a preferred source on Google
