Docker
Displaying 1 to 30 of 74 repositories
Nomic Embed Text v1 is an open‑source, fully auditable text embedding model
2m
10K+
4
Multimodal LLM with video, audio, image, and text understanding for enterprise applications
3m
10K+
4
Multilingual MoE text embedding model with 768D vectors, 100 languages, 512 token context
3m
7.3K
State-of-the-art multilingual MoE text embedding model for retrieval across ~100 languages
3m
6.7K
Efficient 284B MoE language model with 1M token context and multi-mode reasoning capabilities
3m
10K+
3
Multimodal AI model with 35B MoE architecture for coding agents, reasoning, and vision tasks
3m
100K+
5
1T MoE multimodal agentic model with long-horizon coding, swarm orchestration, and native vision
3m
10K+
1
119B MoE model with switchable reasoning mode, multimodal vision, and 256k context window
3m
7.1K
119B parameter hybrid model with reasoning, vision, and code capabilities (1M token context)
3m
10K+
1
Multimodal LLM with 35B parameters for coding, agentic tasks, and vision-language understanding
3m
10K+
Gemma 4: multimodal open AI models by Google, optimized for reasoning, coding, and long context.
4m
50K+
397B MoE model with 17B activation for reasoning, coding, agents, and multimodal understanding
4m
100K+
9
397B-parameter MoE multimodal LLM with 17B active params, 262K context, 201 languages
4m
10K+
1
744B MoE language model with 40B active params for reasoning, coding, and agentic tasks (FP8)
5m
10K+
5
Advanced coding agent model with 80B params (3B active MoE) for code generation and debugging
6m
10K+
1
Efficient 80B MoE coding model with 3B activated params, 256K context, and agentic capabilities
6m
50K+
2
Image generation model, uses a base latent diffusion model plus a refiner.
6m
50K+
7
GLM-4.7-Flash is a top 30B-A3B MoE, balancing strong performance with efficient deployment.
6m
50K+
7
GLM-4.7-Flash is a top 30B-A3B MoE, balancing strong performance with efficient deployment.
6m
10K+
3
Devstral Small 2 is an FP8 instruct LLM for agentic SWE tasks, codebase tooling, and SWE-bench.
6m
10K+
4
FunctionGemma is a 270M open model for fine-tuned, offline function-calling agents on small devices.
7m
10K+
1
FunctionGemma is a 270M open model for fine-tuned, offline function-calling agents on small devices.
7m
10K+
2
Kimi K2 Thinking: open-source agent with deep reasoning, stable tool use, fast INT4, 256k context.
8m
50K+
4
Kimi K2 Thinking: open-source agent with deep reasoning, stable tool use, fast INT4, 256k context.
8m
10K+
2
DeepSeek-V3.2 boosts efficiency and reasoning with DSA, scalable RL, agentic data—IMO/IOI wins.
8m
50K+
11
Ministral 3: compact vision-enabled model with near-24B performance, optimized for local edge use
8m
10K+
4
Ministral 3: compact vision-enabled model with near-24B performance, optimized for local edge use
8m
100K+
4
Multilingual reranking model for text retrieval, scoring document relevance across 119 languages.
8m
10K+
3