Image-Text-to-Text google/gemma-4-31B-it Image-Text-to-Text • 31B • Updated Jul 20 • 8.35M • • 3.66k google/gemma-4-E2B Any-to-Any • 5B • Updated Jul 15 • 77.4k • 451 google/gemma-4-E4B-it Any-to-Any • 8B • Updated Jul 20 • 4.88M • 1.52k
Test Generation Models google/gemma-2-2b Text Generation • 3B • Updated Aug 7, 2024 • 296k • • 693 mistralai/Mistral-7B-Instruct-v0.3 7B • Updated Dec 3, 2025 • 3.11M • 2.83k Qwen/Qwen2.5-Omni-3B Any-to-Any • 6B • Updated Apr 30, 2025 • 720k • 350
Image-Text-to-Text google/gemma-4-31B-it Image-Text-to-Text • 31B • Updated Jul 20 • 8.35M • • 3.66k google/gemma-4-E2B Any-to-Any • 5B • Updated Jul 15 • 77.4k • 451 google/gemma-4-E4B-it Any-to-Any • 8B • Updated Jul 20 • 4.88M • 1.52k
Test Generation Models google/gemma-2-2b Text Generation • 3B • Updated Aug 7, 2024 • 296k • • 693 mistralai/Mistral-7B-Instruct-v0.3 7B • Updated Dec 3, 2025 • 3.11M • 2.83k Qwen/Qwen2.5-Omni-3B Any-to-Any • 6B • Updated Apr 30, 2025 • 720k • 350
Paused Agents LLM Inference & Benchmark Playground ⚡ ZeroGPU demo for OpenAI-compatible LLM benchmarking
Paused Agents Multimodal RAG with Nemotron Embed and Rerank VL 👁 Search recipes with text or image and get summarized results
Paused Agents FoodExtract-Vision Fine-tuned VLM Structued Data Extractor 🍟 Extract food and drink items from any image as structured JSON
ninjals/FoodExtract-Vision-SmolVLM2-500M-fine-tune-v1-VIDEO Image-Text-to-Text • 0.5B • Updated Feb 6 • 8