Thinking Machines’ open 26.4B Inkling 2 Mini loops 12 of its 24 layers three times per token and fits in about 20GB. Most scores are self-reported.
Tag: Hugging Face
A Hugging Face post runs a 180B open MoE model on a 32GB MacBook by streaming experts from the SSD. It’s about 6% behind a rival engine.
SenseTime’s open SenseNova-Loop-9B runs most of its layers twice, buying depth with time instead of memory. Its scores are self-reported.
Tencent’s open 220B Hy4 flash keeps 63.5B parameters in phrase lookup tables. It’s very cheap to run, but trails rivals in independent tests.
Hugging Face’s API for open models now runs via OpenRouter. Code stays the same; the pipes now belong to companies Nvidia and Stripe are buying.
Shanghai AI Lab’s open 321B Sage S2.1 Flash is pitched as a science model, but its card scores agents and office work. The science sits elsewhere.
llama.cpp, the engine behind much local AI, reached 1.0. The real news isn’t speed but a promise: its API won’t break without warning.
Thinking Machines’ 594B open model Inkling 2 Small is on Hugging Face. In training it slipped a network block, and the lab says so openly.
Zyphra’s open ZONOS3-Mini clones a voice from a clip of up to 60 seconds, in 43 languages, on a phone. Its docs say nothing about consent.
Tether’s open 0.8B BotPsy calls tools on-device and doubles its base model’s agent scores. Its makers say: keep it from money. Scores are self-reported.