PrismML · Downloadable
Ternary-Bonsai-2-2B
Understands text and images and responds in text.
- Source listed
- Oct 1, 2026
- Parameters
- 2B
- 4-bit weights only
- ≈ 1 GB
- License
- apache-2.0
WHAT’S NEW
The latest source listings from makers we track, covering language, images, video, audio, and 3D. Catalog checked Oct 28, 2026.
Sorted by the date a source repository was created, which may precede public release. This is a feed of new listings, not confirmed release announcements. Downloadable weights do not automatically mean an open-source license. Coverage and date meanings.
PrismML · Downloadable
Understands text and images and responds in text.
PrismML · Downloadable
Understands text and images and responds in text.
PrismML · Downloadable
Understands text and images and responds in text.
Cloudflare · Downloadable
Understands text and images and responds in text.
Cloudflare · Downloadable
Understands text and images and responds in text.
BAAI · Downloadable
Understands text and images and responds in text.
Microsoft · Downloadable
Designed for coding and software tasks. Understands text and images and responds in text.
Microsoft · Downloadable
Designed for coding and software tasks. Understands text and images and responds in text.
OpenAI · Cloud
Cloud API for vision, chat & writing, reasoning, tool use. Capabilities are catalog-listed, not independently scored.
Anthropic · Cloud
Cloud API for vision, chat & writing, reasoning, tool use. Capabilities are catalog-listed, not independently scored.
Xiaomi MiMo · Downloadable
Generates text for conversations and writing.
Xiaomi MiMo · Downloadable
Generates text for conversations and writing.
Anthropic · Cloud
Cloud API for vision, chat & writing, reasoning, tool use. Capabilities are catalog-listed, not independently scored.
OpenAI · Cloud
Cloud API for vision, chat & writing, reasoning, tool use. Capabilities are catalog-listed, not independently scored.
OpenAI · Cloud
Cloud API for vision, chat & writing, reasoning, tool use. Capabilities are catalog-listed, not independently scored.
Xiaomi MiMo · Downloadable
Understands text and images and responds in text.
Xiaomi MiMo · Downloadable
Generates text for conversations and writing.
Xiaomi MiMo · Downloadable
Generates text for conversations and writing.
xAI · Cloud
Cloud API for vision, chat & writing, reasoning, tool use. Capabilities are catalog-listed, not independently scored.
JetBrains · Downloadable
Generates text for conversations and writing. Supports a reasoning mode.
Liquid AI · Downloadable
Understands text and images and responds in text.
Z.ai · Cloud
Cloud API for vision, video understanding, chat & writing, reasoning, tool use. Capabilities are catalog-listed, not independently scored.
PrismML · Downloadable
Generates text for conversations and writing.
Qwen · Alibaba · Cloud
Cloud API for vision, video understanding, audio understanding, chat & writing, reasoning, tool use. Capabilities are catalog-listed, not independently scored.
Capability tags distinguish a model that reads images from one that creates them. Each listing links to its source and a permanent profile, so you can inspect its license and compare it with a model you already know.
No. The current feed tracks public Hugging Face metadata from selected makers. It can miss untracked makers, cloud-only releases, and records beyond a source’s retrieval limit. Announced models without a source listing are not included. Check Sources & methodology for the current coverage.
Listings update with the catalog automatically. A missing or delayed source can leave older information visible; each model profile shows when it was checked.