ai/granite-docling

Docker

Granite Docling is a multimodal model for efficient document conversion.

ai/qwen3-coder-next-vllm

Docker

Advanced coding agent model with 80B params (3B active MoE) for code generation and debugging

ai/gpt-oss-safeguard

Docker

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

ai/embeddinggemma

Docker

Embedding Gemma is a state-of-the-art text embedding model from Google DeepMind

ai/glm-4.7-flash-vllm

Docker

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

ai/nomic-embed-text-v1.5

Docker

Nomic Embed Text v1 is an open‑source, fully auditable text embedding model

ai/qwen3-embedding-vllm

Docker

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

ai/devstral-small-2

Docker

Devstral Small 2 is an FP8 instruct LLM for agentic SWE tasks, codebase tooling, and SWE-bench.

ai/qwen3-reranker-vllm

Docker

Multilingual reranking model for text retrieval, scoring document relevance across 119 languages.

ai/gpt-oss-vllm

Docker

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

ai/mistral-nemo

Docker

Mistral fine-tuned via NVIDIA NeMo for smoother enterprise use

ai/qwen3.6

Docker

Multimodal AI model with 35B MoE architecture for coding agents, reasoning, and vision tasks

ai/qwen3.5-safetensors

Docker

397B-parameter MoE multimodal LLM with 17B active params, 262K context, 201 languages

ai/magistral-small-3.2

Docker

24B multimodal instruction model by Mistral AI, tuned for accuracy, tool use & fewer repeats

ai/seed-oss

Docker

Designed for reasoning, agent and general capabilities, and versatile developer-friendly features

ai/qwen3-reranker

Docker

Multilingual reranking model for text retrieval, scoring document relevance across 119 languages.

ai/smolvlm

Docker

SmolVLM: lightweight multimodal model for video, image, and text analysis, optimized for devices.

redhat/granite-3-2b-instruct

Red Hat, Inc.

IBM's Granite 3.0 large language model (LLM), optimized for local large language model operations

ai/mxbai-embed-large

Docker

mxbai-embed-large-v1 is a top English embed model by Mixedbread AI, great for RAG and more.

ai/smollm2-vllm

Docker

SmolVLM: lightweight multimodal model for video, image, and text analysis, optimized for devices

ai/glm-5-safetensors

Docker

744B MoE language model with 40B active params for reasoning, coding, and agentic tasks (FP8)

ai/devstral-small

Docker

Agentic coding LLM (24B) fine-tuned from Mistral-Small-3.1 with a 128K context window

ai/granite-4.0-nano

Docker

Granite-4.0-nano: lightweight instruct model trained via SFT, RL, and merging on diverse data.

ai/functiongemma

Docker

FunctionGemma is a 270M open model for fine-tuned, offline function-calling agents on small devices.

ai/granite-4.0-h-tiny

Docker

7B long-context instruct model with RL alignment, IF, tool use, and enterprise optimization.

ai/qwq

Docker

Experimental Qwen variant—lean, fast, and a bit mysterious

ai/moondream2

Docker

An open-source visual language model that interprets images via text prompts, fast and powerful.

redhat/granite-7b-lab-gguf

Red Hat, Inc.

4-bit quantized version of model Granite-7b-lab

ai/granite-embedding-multilingual

Docker

Granite Embedding Multilingual is a 278 million parameter, encoder‑only XLM‑RoBERTa‑style

ai/granite-4.0-h-small

Docker

32B long-context instruct model with RL alignment, IF, tool use, and enterprise optimization.