Liquid AI ships LFM2.5-24B-A2B, a 24B MoE with just 2B active params, open-weight on Hugging Face. 184 tokens/s on an M5 Max, 131K context. "Built for fast on-device agents" is doing heavy lifting. The benchmarks back it, but they focus on harness work, so your mileage may vary.Liquid AI: https://www.liquid.ai/blog/lfm2-5-24b-a2b#OpenWeights #LLM #LiquidAI #LocalAI #Moe
Related
📈 Olud Index at 138. Stars are running 2.14x normal — the AI ecosystem is building far above baseline pace. See what's d...
📈 Olud Index at 138. Stars are running 2.14x normal — the AI ecosystem is building far above baseline pace. See what's driving that surge on olud.ai.https://olud.ai/dashboard.html#...
Rui Ma of TechBuzz China explains why China's AI labs aren’t chasing export markets – they’re fighting a brutal domestic...
Rui Ma of TechBuzz China explains why China's AI labs aren’t chasing export markets – they’re fighting a brutal domestic price war. That competition may be lowering global AI costs...
Firm embroiled in Nvidia scandal linked to Australian newsagent workerBy Jasper WellsThe Australian subsidiary of the fi...
Firm embroiled in Nvidia scandal linked to Australian newsagent workerBy Jasper WellsThe Australian subsidiary of the firm at the centre of the alleged Nvidia spy scandal lists a n...