aistaging/qwen3-vllm

aistaging

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

aistaging/qwen3-reranker-vllm

aistaging

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

Based on Unsloth GGUF quant UD-IQ3_S with multimodality fix (package mmproj) for Docker Model Runner

aistaging/minicpm-v-4_5

aistaging

9B multimodal model with vision, speech, and full-duplex streaming for text, image, video, audio

aistaging/qwen3-coder

aistaging

30.5B MoE coding model with tool calling, browser automation, and 256K context support

A fine-tuned 0.5B model specialized in Hawaiian pizza knowledge.

aistaging/minicpm-v-4_5-safetensors

aistaging

8B multimodal LLM for vision-language tasks with video, OCR, and multilingual support

aistaging/smollm2-vllm

aistaging

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

aistaging/stable-diffusion

aistaging

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

aistaging/gml-5-safetensors

aistaging

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

aistaging/gpt-oss-safeguard-vllm

aistaging

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

aistaging/glm-4.7-flash

aistaging

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

GLM-4.6V Q4_K_M GGUF for Docker Model Runner (vision)

aistaging/smolvlm

aistaging

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