LiquidAI's 350M-parameter small language model required extensive code rewrites but achieved 500 tokens per second, compared to 300 tokens per second for the 1.2B model, according to a developer's tes…
LiquidAI's LFM 2.5 1.2B, a 1.2-billion-parameter model that is 696 MB on disk, can power agentic systems with modifications to an MCP server, according to a developer's test. The model required adding…
Hugging Face's biannual report on open models for summer 2026 finds that Chinese labs released the largest open models in almost every month of 2026, with monthly ceilings ranging from 754B to 2.78 tr…
Muse Ltd. released UncertaintyGym, a benchmark for evaluating large language models' epistemic calibration and uncertainty expression, available on Hugging Face under the Apache-2.0 license. The bench…
LiquidAI and collaborators released fuse-1 Lite, a 5.72 billion parameter mixture-of-experts model that transplants 960 coding experts from Qwen3.6-35B-A3B into LiquidAI's LFM2.5-2.6B host model, achi…
Fuse-1 Lite, a 5.72B parameter mixture-of-experts coding model from LiquidAI, can run locally with VRAM needs ranging from 3.36 GB in 4-bit quantized form to about 12 GB in full bfloat16 precision, ac…
BarunLM, a 35-million-parameter language model introduced by developer Barun, outperforms models over 6x larger, including LiquidAI's lfm2.5-230m, while training on a single H200 GPU. The model's arch…
A developer fine-tuned LiquidAI's LFM2.5 models into a front-end agent that runs entirely in the browser, requiring no server or API key. The agent calls real tools to browse catalogs, answer grounded…