Liquid AI ships LFM2.5-24B-A2B: 24B total, 2.45B active, targets Qwen3.6-35B locally
JosephJacks_ · x · 2026-10-14
Liquid AI released LFM2.5-24B-A2B, the largest of the 2.5 family — an efficient local model for laptops/PCs running multi-step agent tasks. Specs: 24B total / 2.45B active params, 131K context, 128K vocab, 33T pretraining tokens, reasoning-capable, easy to fine-tune. Liquid claims it matches or beats Qwen3.6-35B-A3B (50% more params) on agentic/tool-use tasks; the benchmark chart shows a big lead on AutomationBench (27.69 vs 8.72) and wins on BFCLv4, ToolSandbox, LiveClaw, with parity on GPQA Diamond and MATH-500. Open base and post-trained weights are on Hugging Face.
Related event: LiquidAI Releases LFM2.5-24B-A2B, an On-Device MoE Reasoning Model(13 posts)→
More from Models
- Nathan Lambert slams Meta's Muse Open License as 'trash' — natolambert · 2026-10-16
- Google launches Gemini 4 Argon to Ultra and Pro subscribers, touting physics and 3D skills — ShikharMurty · 2026-10-16
- Google gives X users early access to test Argon, not just companies — lyraxana · 2026-10-16
- Grok Voice 3.0 Tops Design Arena Speech Leaderboard, Up 7.4 Points — XFreeze · 2026-10-16
- Robotics LLMs tested on 16 tasks: GPT-6 Astra hits 17.2% success vs Fable's 9.1% — pabbeel · 2026-10-16
- Meta open-sources Muse Spark: top US open model, scores just below DeepSeek — bindureddy · 2026-10-16