OpenAI's Decisions API entered public beta, offering predicate, choice and score question types that return probabilities rather than generated text, priced at ten cents per million input tokens with …
LiquidAI published LFM2-350M-PII-Extract-JP, a 350M-parameter text-generation model for Japanese personally identifiable information extraction, to its Hugging Face repository under the LiquidAI organ…
LiquidAI released LFM2.5-VL-DSpark, a 279.5M-parameter speculative decoding drafter for its LFM2.5-VL-3B vision-language model that adds 8.9% to the target model's parameter count while delivering dec…
A developer got the 230M-parameter LiquidAI LFM2.5-230M-Q5_K_M.gguf model working with a local MCP server after switching from 4-bit to 5-bit quantization, following an earlier setup that ran the 350M…
Fine-tuning LiquidAI's LFM2.5-350M model with Group Relative Policy Optimization (GRPO) using the TRL library improved its IFStruct benchmark score from 22.6% to 29.7% in just 100 training steps, acco…
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…