Liquid AI releases LFM2.5-24B-A2B, an open-weight 24B/2B-active MoE built for on-device agents
Confirmed
The takeaway
On 13 Oct 2026 Liquid AI released LFM2.5-24B-A2B, a reasoning mixture-of-experts model with 24B total and 2B active parameters, open weights under its LFM license, and a 131K-token context (up from 32K in LFM2-24B-A2B).
Status
- Claim
Confirmed
- Our reporting
- High confidence
- Importance
- 2 of 5
- Last verified
- 15 October 2026
Your AI and this story
- GPT-6 Astra166 days after its cutoff
- Claude Opus 5.5105 days after its cutoff
- Gemini 4 Argon196 days after its cutoff
- Grok 4.7135 days after its cutoff
None of these four assistants can know about it. The closest, Claude Opus 5.5, stops 105 days before it.
Key facts
- Hugging Face: LiquidAI/LFM2.5-24B-A2B (repo created 12 Oct, updated 13 Oct; license ‘lfm1.0’ per the HF API); a base model LFM2.5-24B-A2B-Base is also published
- Architecture (blog): 24B total / 2B active per token, 64 experts per block, top-4 routing; reasoning-only model; context 131,072 tokens
- Vendor benchmarks vs Qwen3.6-35B-A3B: AutomationBench 27.69 vs 8.72; LiveClaw 48.09 vs 38.19; ToolSandbox 80.71 vs 75.02; IFEval 96.75 vs 93.06; IFBench 74.69 vs 64.21; BFCLv4 65.01 vs 65.00; GPQA Diamond 74.42 vs 83.69; SWE-bench Verified (OpenCode) 51.00 vs 66.20
- Speed (vendor): 184 tokens/s on Apple M5 Max; up to 21K output tokens/s on one NVIDIA B300
- API on Liquid Console: $0.10 per 1M input tokens ($0.05 cached), $1.00 per 1M output tokens; day-one llama.cpp (GGUF), MLX, vLLM, SGLang and ONNX support
- Hacker News: 125 points on 14 Oct
What happened
Liquid AI, known for small “liquid foundation models” aimed at edge devices, released a larger sparse model meant to run agents locally. It is reasoning-only and uses only 2B active parameters per token. Liquid recommends pairing it with retrieval or web search for knowledge-heavy tasks and mentions local agent harnesses such as Hermes Agent. All benchmark and speed numbers are Liquid’s own.
Why it matters
Small active-parameter MoEs are becoming the default design for agents that run on laptops. This one claims to beat a larger Qwen MoE on tool use and instruction following, while trailing it on hard knowledge and coding benchmarks.
Sources
3 sources from 3 sites. Numbers match the chips in the text.
3 sources: 2 primary, 1 reaction
Primary
- Liquid AI: LFM2.5-24B-A2B, built for fast on-device agentsliquid.ai, official
- Hugging Face: LiquidAI/LFM2.5-24B-A2Bhuggingface.co, code
Reactions
- Hacker News discussion (125 points)news.ycombinator.com, discussion
Changes
- Filed from Liquid AI’s blog and the Hugging Face API (HN front page)