aiqbench analysis
Liquid AI's LFM2.5-2.6B demonstrates a significant architectural shift toward efficient, on-device agentic reasoning by combining short convolution blocks with GQA for high-speed local inference. This open-weight model enables multi-step tool use and long-context processing entirely offline, addressing critical privacy needs in regulated sectors like healthcare and defense without relying on cloud APIs. The release underscores the growing viability of running complex autonomous agents directly on consumer hardware rather than depending solely on large-scale data centers.
Liquid AI Releases LFM2.5-2.6B: An On-Device Agentic Model With 128K Context, Tool Calling, And Open Weights
Liquid AI released LFM2.5-2.6B, an agentic model that plans, calls tools, and completes multi-step tasks entirely on-device. The 2.69B parameter model pairs 22 double-gated short convolution blocks with 8 GQA blocks across 30 layers, handles 131,072 tokens of context, and decodes at 220 tokens/s on an M5 Max in under 2.5 GB. Open weights ship in GGUF, MLX, and ONNX. The post Liquid AI Releases LFM2.5-2.6B: An On-Device Agentic Model With 128K Context, Tool Calling, And Open Weights appeared first on MarkTechPost.
Liquid AI released LFM2.5-2.6B, an agentic model that runs entirely on-device. It plans, calls tools, and works through multi-step tasks on phones, laptops, PCs, and robots. The model has 2.69B total parameters, a 131,072-token context window, and a 128,000-token vocabulary. Pre-training used approximately 34 trillion tokens. Two checkpoints shipped: LFM2.5-2.6B-Base for fine-tuning, and LFM2.5-2.6B post-trained for agentic workloads. Because inference…
Excerpt shown under the publisher's RSS terms · 60 words · full text and figures are on the publisher's site
Related coverage
Liquid AI Releases LFM2.5-VL-3B: A 3B Vision-Language Model That Reads Screens, Grounds Objects, and Calls Tools On-Device
MarkTechPost · Aug 13, 2026
[AINews] TypeSafe/Jev at >$100M ARR, $7.5B valuation 3 weeks after launch
Latent Space · Oct 10, 2026
Liquid AI Releases LFM2.5-DSpark Draft Models That Deliver Up to 3.18x Faster Decoding Without Changing Model Outputs
MarkTechPost · Aug 20, 2026
Google DeepMind Ships Three Physical AI Models For Whole Body Control, Dexterity And Multi Robot Collaboration
MarkTechPost · Jul 30, 2026