OpenModelStats

nvidia AI Models

Tracked by OpenModelStats since Aug 23, 2026 · View on Hugging Face ↗

Tracked models
456
Downloads 30D
57.5M
Total downloads
420.5M
Total likes
50.5K
Gained 7D
—

Most downloaded

  1. 1Qwen3.6-35B-A3B-NVFP4Jun 12, 202612.6M
  2. 2Gemma-4-31B-IT-NVFP4Jul 13, 20262.3M
  3. 3bigvgan_v2_22khz_80band_256xSep 5, 20242.1M
  4. 4parakeet-ctc-1.1bAug 5, 20261.8M
  5. 5Gemma-4-26B-A4B-NVFP4May 11, 20261.7M
  6. 6Nemotron-3-Nano-Omni-30B-A3B-Reasoning-NVFP4May 5, 20261.5M
  7. 7NVIDIA-Nemotron-3-Super-120B-A12B-NVFP4May 1, 20261.5M
  8. 8GLM-5.2-NVFP4Jun 26, 20261.3M
  9. 9Qwen3.6-27B-NVFP4Jun 30, 20261.2M
  10. 10nemotron-3.5-asr-streaming-0.6bAug 5, 20261M

Recently updated

  1. 1NVIDIA-Nemotron-Parse-2.0Aug 22, 202620.7K
  2. 2llama-nemotron-rerank-vl-1b-v2Aug 21, 202651.5K
  3. 3Cosmos3-EdgeAug 20, 2026789.2K
  4. 4Kimi-K3-NVFP4Aug 19, 20264,602
  5. 5GR00T-HAug 19, 2026380
  6. 6NVIDIA-NemotronLabs-VoiceChat-11BAug 19, 20262,613
  7. 7Nemotron-Labs-Audex-2BAug 18, 20261,041
  8. 8cmdAug 18, 20260
  9. 9NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4Aug 17, 2026581.7K
  10. 10DeepSeek-V4-Flash-nvfp4-DSparkAug 15, 202614.5K

All models

All tracked models published by nvidia
ModelDL 30D7D
Cosmos-Reason2-8Bnvidia/cosmos-reason2-8b645K—
MiniMax-M2.5-NVFP4nvidia/minimax-m2.5-nvfp4599.4K—
Llama-3.3-70B-Instruct-NVFP4nvidia/llama-3.3-70b-instruct-nvfp4586.3K—
NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4nvidia/nvidia-nemotron-3.5-lightning-30b-a3b-nvfp4581.7K—
NVIDIA-Nemotron-3-Nano-30B-A3B-NVFP4nvidia/nvidia-nemotron-3-nano-30b-a3b-nvfp4532.8K—
NVIDIA-Nemotron-3-Nano-4B-BF16nvidia/nvidia-nemotron-3-nano-4b-bf16528.4K—
llama-embed-nemotron-8bnvidia/llama-embed-nemotron-8b490.5K—
Qwen3.5-122B-A10B-NVFP4nvidia/qwen3.5-122b-a10b-nvfp4485.9K—
Qwen3-8B-FP8nvidia/qwen3-8b-fp8468.6K—
NVIDIA-Nemotron-Labs-3-Puzzle-75B-A9B-NVFP4nvidia/nvidia-nemotron-labs-3-puzzle-75b-a9b-nvfp4441.9K—
NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16nvidia/nvidia-nemotron-3-ultra-550b-a55b-bf16426.1K—
Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF16nvidia/nemotron-3-nano-omni-30b-a3b-reasoning-bf16409.5K—
NVIDIA-Nemotron-Nano-9B-v2nvidia/nvidia-nemotron-nano-9b-v2390K—
parakeet-tdt-0.6b-v2nvidia/parakeet-tdt-0.6b-v2382.6K—
NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4nvidia/nvidia-nemotron-3-ultra-550b-a55b-nvfp4329.6K—
segformer-b0-finetuned-ade-512-512nvidia/segformer-b0-finetuned-ade-512-512314.1K—
segformer-b2-finetuned-ade-512-512nvidia/segformer-b2-finetuned-ade-512-512310.9K—
DeepSeek-V4-Flash-NVFP4nvidia/deepseek-v4-flash-nvfp4308.7K—
Nemotron-3-Embed-1B-BF16nvidia/nemotron-3-embed-1b-bf16297K—
Cosmos3-Nanonvidia/cosmos3-nano285.4K—
Qwen3-VL-235B-A22B-Instruct-NVFP4-MLPerf-Inference-Closed-V6.1-FP8-KVnvidia/qwen3-vl-235b-a22b-instruct-nvfp4-mlperf-inference-closed-v6.1-fp8-kv282.5K—
MiniMax-M3-NVFP4nvidia/minimax-m3-nvfp4281.9K—
Qwen3.5-397B-A17B-NVFP4nvidia/qwen3.5-397b-a17b-nvfp4259.9K—
Cosmos-Predict2-2B-Video2Worldnvidia/cosmos-predict2-2b-video2world245K—
Llama-3_3-Nemotron-Super-49B-v1_5-FP8nvidia/llama-3_3-nemotron-super-49b-v1_5-fp8239.4K—