Liquid AI 2.6B Model Matches DeepSeek in Tool Calling, 3.7x Faster
Liquid AI's 2.6B-parameter LFM2.5 model achieves 90 tokens/s on Apple M5 Pro and matches DeepSeek-V4 in tool calling while being 3.7x faster on RTX 5090s, showcasing strong edge potential.
2026-08-06 ~ 2026-08-07 · 3 related posts
- Episode 1: Liquid AI Releases 2.6B On-Device Agent Model LFM2.5(2026-08-04, 18 posts)
- Episode 2: 2.6B Model Powers Browser-Based Research Agent, Open Source(2026-08-04, 5 posts)
- Episode 3: Liquid AI 2.6B Model Matches DeepSeek in Tool Calling, 3.7x Faster(2026-08-06, 3 posts)
- Episode 4: Liquid AI Releases LFM 2.5 with 2.6B Parameters(2026-08-09, 2 posts)
- Testing Liquid AI's LFM2.5 2.6B: 90t/s Speed but Fails at Tool Calling — curiousily_ · 2026-08-06
- Liquid AI's New Model Matches DeepSeek in Agentic Tool Calls at 3.7x Speed — JosephJacks_ · 2026-08-07
- Edge Model LFM2.5 Matches DeepSeek-V4 in Tool Calling at 3.7x the Speed — maximelabonne · 2026-08-07