Which open-source LLM has surprised you the most this year, and how are you using it?
OPEN SOURCE
-
OpenBench 0.3.0 Release: New Features and Improvements
By
–
OpenBench 0.3.0 is here. And it’s stacked.
-
CodeGemma FIM Support Expected in Upcoming Release
By
–
I *really* hope a new CodeGemma with FIM support is one of the things in the oven! 😀
-
Flowise and Workday Partner to Democratize AI Agent Building
By
–
6/ Flowise x Workday We share the same vision as Workday – empowering teams to build and scale AI agents, without deep technical expertise. Together, we're deeply committed to the open-source community and investing to make Flowise even better.
-
Flowise: Building LLM Applications Visually with No-Code
By
–
1/ Beginnings Flowise began with a simple vision – to help people build LLM applications visually using frameworks like @langchain and @llama_index
. We launched publicly in April 2023, and it immediately resonated with the developer community. -
LM Studio and Ollama lack tool support capabilities
By
–
Neither the LM Studio nor the Ollama builds support tools, so I've not tried to get that to work
-
Google releases Gemma 3 with 270 million parameters
By
–
270 million (not billion) parameters! https://
huggingface.co/google/gemma-3
-270m
… -
Google Releases Gemma3 270M Tiny LLM on KerasHub
By
–
Google just dropped a new tiny LLM with outstanding performance — Gemma3 270M. Now available on KerasHub. Try the new presets `gemma3_270m` and `gemma3_instruct_270m`!
-
Guardrails AI Launches: Long-time Follower Shares Support
By
–
I have followed @guardrails_ai since they were founded and retweeted their previous launches.
-
Meta releases DINOv3 computer vision model under commercial license
By
–
To help foster innovation and collaboration in the computer vision community, we’re releasing DINOv3 under a commercial license with a full suite of pre-trained backbones, adapters, training and evaluation code, and (much!) more. Find them here: https://
github.com/facebookresear
ch/dinov3
…