Filter by
(1)
SmolVLM: lightweight multimodal model for video, image, and text analysis, optimized for devices.
1y
10K+
4
Multimodal LLM with 35B parameters for coding, agentic tasks, and vision-language understanding
7m
10K+
119B parameter hybrid model with reasoning, vision, and code capabilities (1M token context)
7m
10K+
1
Base image for the Google Antigravity kit for Docker Sandboxes
9h
10K+
1
Base image for the gstack (Claude Code + Garry's Stack) kit for Docker Sandboxes
10h
10K+
2
7B long-context instruct model with RL alignment, IF, tool use, and enterprise optimization.
1y
10K+
4
IBM's Granite 3.0 large language model (LLM), optimized for local large language model operations
2y
10K+
8
An open-source visual language model that interprets images via text prompts, fast and powerful.
1y
10K+
2
32B long-context instruct model with RL alignment, IF, tool use, and enterprise optimization.
1y
10K+
1
3B long-context instruct model with RL alignment, IF, tool calling, and enterprise readiness.
1y
10K+
2
Anthropic's Claude Code as a mixin — the native install in an overlay, with the `anthropic` cre...
4h
10K+
IBM's Granite 3.0 large language model (LLM), optimized for local large language model operations
2y
10K+
1
Multilingual MoE text embedding model with 768D vectors, 100 languages, 512 token context
7m
10K+