Ant Ling releases Ling-3.0-flash-Fin weights on Hugging Face
FellMentKE · x · 2026-09-04
Following the Ant Ling 3.0-flash launch, the Fin variant's weights are now available on Hugging Face. The model uses the Bailing V3 architecture with a chat template supporting a controllable thinking toggle and function calling.
The poster notes that a launch and an evaluation framework answer different questions: one gives builders a model to adapt, while the other gives researchers a more detailed way to examine where an agent succeeds, fails, or needs closer review. The official Discord is open for updates and discussion.
More from Models
- More GPT-6 codenames spotted: GPT-6-Pro and mysterious 'WM' suffix fuel world model speculation — scaling01 · 2026-09-04
- Meta's speech model targets messy real rooms as the ears for its glasses and agent stack — heypearlai · 2026-09-04
- Meta claims top spot on Artificial Analysis for streaming speech-to-text and diarization at launch — heypearlai · 2026-09-04
- OpenAI ships GPT-6 Astra; Brockman suggests it could be AGI — steph_palazzolo · 2026-09-04
- Follow-up links added to GPT-6 Astra leak thread — Angaisb_ · 2026-09-04
- GPT-6-Astra, GPT-6-Pro codenames spotted in ChatGPT frontend, fueling unconfirmed rumors — Angaisb_ · 2026-09-04