Verified, then logged.
Sun 22 Nov 2026 · 00:13 KST / 15:13 UTC한국어 | ENSearch /

IT

Agent frameworks, SDKs and CLIs, open source releases, local inference and coding tools.

Hugging Face unifies generation cache names in Transformers

Support for the old cache argument names ends at different versions for `forward` and `generate`.

Last 7 daysNov 17 – Nov 21

Thinking Machines Lab releases Inkling 2 Mini weights

In Thinking Machines Lab’s tests, a research model scored higher on long-context tasks when its middle layers ran more times.
AI illustration

Hugging Face routes language models through OpenRouter

Failed requests are retried with another provider, while support for users' own provider keys ends for language models.

1 week agoNov 10 – Nov 15

Hugging Face unifies model export return format

The update brings exported models under a shared interface for sharing and execution, while changing how developers save them.
In a dim server aisle, an engineer seen from behind checks a laptop connected to an open GPU server, its screen showing a green bar starting beneath an amber error block. AI-generated image

Hugging Face proposes a shared decision-model interface

The proposed interface brings probabilities for predefined answers and different question types under a common input and output contract.
Image from Hugging Face

Motif 4 is due as open weights in first quarter of next year

Predecessor Motif 3 is licensed under `MIT`, but public documents do not state the licence terms for the follow-up model.
In a server room at a Korean AI startup, an engineer seen from behind slides a server packed with graphics accelerators into a rack. AI-generated image

2 weeks agoNov 04

IBM's 20B slide model Palette arrives with no stated licence

IBM researchers report second place on the three-domain PresentBench mean, but their blog post does not say where the weights are distributed or what commercial terms apply.
A desk monitor in a dim meeting room displays a grid of wordless presentation slide thumbnails, one with overlapping shapes spilling past its edge. AI-generated image

3 weeks agoOct 27 – Oct 31

Nanbeige releases 33B model Nanbeige4.3-33B under Apache-2.0

The Terminal-Bench 2.1 score of 80.9 comes from the developer's own evaluation, and training data sources and minimum VRAM are not confirmed in public documents.
An open workstation with two graphics cards sits on a wooden desk as an out-of-focus person connects an external solid-state drive. AI-generated image

Mistral publishes Large 4 weights under modified MIT licence

Commercial use is allowed, but a model-as-a-service business needs a separate commercial licence.
A compact desktop workstation connected to a stack of external drives runs on a wooden desk in a small office, with a developer blurred in the background and seen from behind. AI-generated image

Liquid AI's LFM3 models run on Linux and Windows with Ollama

The models now run beyond Apple silicon, but the release notes do not give their licence or minimum VRAM.
An open-sided desktop PC with a graphics card sits beside a closed silver laptop on a home desk, with a blurred terminal window on the monitor behind them. AI-generated image

Ollama adds Liquid AI's LFM3 models, on Apple hardware first

The release notes do not name a licence or give a date for Linux and Windows support.
On a desk at dusk, a silver laptop glows with blurred terminal output while a black desktop PC and monitor sit powered off behind it. AI-generated image

Oct 2026Oct 15 – Oct 24

Ollama v0.40.11 brings macOS speech generation and d3 models

The release notes state no licence and give no VRAM requirements for each d3 size
A small speaker wired to a laptop sits in sharp focus on a home desk while an out-of-focus person, seen from behind, leans in to listen. AI-generated image

Apache-2.0 coding model Flint runs first on macOS via Ollama

The `Apache-2.0` model has 40B parameters, but the release notes give no minimum VRAM or training data sources.
A silver laptop displays blurred code on a developer's desk, beside a powered-off desktop tower and an unplugged graphics card. AI-generated image

Hugging Face introduces TorchNeuron for AWS's Trainium chips

Hugging Face says running its models on AWS Trainium is easier than ever.
A server tray pulled halfway out of a data center rack reveals a dense row of AI accelerator modules, while an out-of-focus engineer works on a laptop with their back to the camera. AI-generated image

Ollama v0.40.6 introduces q2_0 tensor and file types to GGUF

The release notes do not say what clef is or what VRAM q2_0 requires.
An open desktop PC with an unbranded graphics card and NVMe drive sits on a warmly lit desk, with a blurred terminal window glowing on the monitor behind it. AI-generated image

Transformers v5.20.0 breaks code with deprecated cache calls

Code that calls the removed cache methods needs changes, and the release notes do not say how far expert-parallel inference has slowed.
Past the blurred back of a developer in warm lamplight, a monitor shows code with changed lines marked in red and green beside an open workstation holding several graphics cards. AI-generated image

FLUX.3 Image Klein comes to Hugging Face's Diffusers library

Hugging Face announced the addition through the title of a blog post published on 15 Oct 2026.
On a sunlit desk, a monitor beside a compact computer displays a grid of images progressing from coarse noise to sharp pictures. AI-generated image

17 in totalWritten by Jiyul SeoRSS feed