20+ models
Llama 3.2 Vision is a collection of instruction-tuned image reasoning generative models in 11B and 90B sizes.
Wizard Vicuna is a 13B parameter model based on Llama 2 trained by MelodysDreamj.
A compact and efficient vision-language model, specifically designed for visual document understanding, enabling automated content extraction from tables, charts, infographics, plots, diagrams, and more.
Wizard Vicuna Uncensored is a 7B, 13B, and 30B parameter model based on Llama 2 uncensored by Eric Hartford.
Hermes is a large language model fine-tuned on proprietary datasets curated for training mental health therapists.
Nemotron 3.5 Bolt is NVIDIA’s compact vision-language model for local coding, reasoning, and tool use.
Nemotron 3.5 Super is NVIDIA’s vision-language model for coding, reasoning, tool use, and document understanding
NVIDIA Nemotron 3 Nano Omni is a multimodal large language model that unifies video, audio, image, and text understanding to support enterprise-grade Q&A, summarization, transcription, and document intelligence workflows.
A Pocket-Sized MLLM for Ultra-Efficient Image and Video Understanding on Your Phone
A GPT-4o Level MLLM for Single Image, Multi Image and High-FPS Video Understanding on Your Phone
Vicky is a 4.1GB model from the Llama model family, with 7 billion parameters. It is quantized to 4-bit precision. The model is designed for Open stack Tool selection for user or developer. License: Apache License Version 2.0
VitalPet-RD is an AI research and development assistant for companion animal nutrition and pet health products.
This version of bellman is finetuned from llama-3.1-instruct-8b. It's finetuned for prompt question answering, based on a dataset created from Swedish wikipedia, with a lot of Sweden-centric questions.
The extended version of fine-tuned QWEN model that includes more quality training examples both from Claude Sonnet 3.5 (NEW) and Linux Command Library (https://linuxcommandlibrary.com)
Fine Tuned For Hermes-style function calling with VibeThinker 3b
A self-improving family of open-source models for agentic coding, correctly exported with vision, reasoning and tool capabilities
Vidya is a fine-tuned Qwen3.5-9B tutoring assistant for Indian students — NCERT Classes 6–12, IIT-JEE, and NEET — with step-by-step reasoning and misconception correction.
Vidya Kisan is a fine-tuned Qwen3.5 offline agronomic advisory model for Indian smallholder farmers — crop disease, pest IPM, irrigation and nutrients — with least-harm-first advice and KVK escalation. Research preview
Fine-tuned Qwen3.5-9B with distilled reasoning and full vision support. 883 tensors (427 text + 441 vision + 15 MTP) — vision tower preserved byte-for-byte from base via llama-export-lora merge.
Fine-tuned Qwen3.5-9B with distilled reasoning and full vision support. 883 tensors — vision tower preserved byte-for-byte from base. R5 was the first vision-capable distilled model.