ai/gemma3

Docker

Google’s latest Gemma, small yet strong for chat and generation

ai/qwen3

Docker

Qwen3 is the latest Qwen LLM, built for top-tier coding, math, reasoning, and language tasks.

ai/llama3.2

Docker

Solid LLaMA 3 update, reliable for coding, chat, and Q&A tasks

ai/gpt-oss

Docker

OpenAI’s open-weight models designed for powerful reasoning, agentic tasks

ai/smollm2

Docker

Tiny LLM built for speed, edge devices, and local development

ai/deepseek-r1-distill-llama

Docker

Distilled LLaMA by DeepSeek, fast and optimized for real-world tasks

ai/qwen3-coder

Docker

Qwen3-Coder is Qwen’s new series of coding agent models.

ai/qwen3-vl

Docker

The most advanced Qwen model yet, with major gains in text, vision, video, and reasoning.

ai/qwen2.5

Docker

Versatile Qwen update with better language skills and wider support

ai/gemma3n

Docker

Efficient multimodal AI for text, image, audio, and video on low-resource devices.

ai/gemma3-qat

Docker

Google’s latest Gemma, in its QAT (quantization aware trained) variant

ai/phi4

Docker

Microsoft’s compact model, surprisingly capable at reasoning and code

ai/llama3.3

Docker

Newest LLama 3 release with improved reasoning and generation quality

ai/mistral

Docker

Efficient open model with top-tier performance and fast inference

ai/ministral3

Docker

Ministral 3: compact vision-enabled model with near-24B performance, optimized for local edge use

ai/kimi-k2

Docker

Kimi K2 Thinking: open-source agent with deep reasoning, stable tool use, fast INT4, 256k context.

ai/deepcoder-preview

Docker

DeepCoder-14B-Preview is a code reasoning LLM fine-tuned to scale up to long context lengths

ai/deepseek-v3.2-vllm

Docker

DeepSeek-V3.2 boosts efficiency and reasoning with DSA, scalable RL, agentic data—IMO/IOI wins.

ai/smollm3

Docker

SmolLM3 is a 3.1B model for efficient on-device use, with strong performance in chat

ai/gemma3-vllm

Docker

Google’s latest Gemma, small yet strong for chat and generation

ai/glm-4.7-flash

Docker

GLM-4.7-Flash is a top 30B-A3B MoE, balancing strong performance with efficient deployment.

ai/llama3.1

Docker

Meta’s LLama 3.1: Chat-focused, benchmark-strong, multilingual-ready.

ai/qwen3-coder-next

Docker

Efficient 80B MoE coding model with 3B activated params, 256K context, and agentic capabilities

ai/qwen3-embedding

Docker

Qwen3 Embedding: multilingual models for advanced text/ranking tasks like retrieval & clustering.

ai/ministral3-vllm

Docker

Ministral 3: compact vision-enabled model with near-24B performance, optimized for local edge use

ai/qwen3.5

Docker

397B MoE model with 17B activation for reasoning, coding, agents, and multimodal understanding

ai/kimi-k2-vllm

Docker

Kimi K2 Thinking: open-source agent with deep reasoning, stable tool use, fast INT4, 256k context.

ai/granite-docling

Docker

Granite Docling is a multimodal model for efficient document conversion.

ai/stable-diffusion

Docker

Image generation model, uses a base latent diffusion model plus a refiner.

ai/gpt-oss-safeguard

Docker

Safety reasoning models for policy-based text classification and foundational safety tasks.