AImodelsComparison.com 1,000 models
Menu
Models Best of Trending Can I run it? Methodology About
1,000 models · refreshed nightly

Models that run on RTX 4090 · 24 GB

Every model in the catalog with its licence, estimated VRAM and daily-tracked downloads. Filters update the URL — share any view.

Task
All text-generation 400 text-to-image 150 ASR 88 image-text-to-text 80 sentence-similarity 55 feature-extraction 45 translation 43 text-classification 39 image-classification 32 token-classification 21 text-to-speech 12 audio-classification 10 object-detection 10 image-segmentation 8 summarization 7
Runs on
Any RTX 3060 · 12 GB RTX 4070 · 16 GB RTX 4090 · 24 GB 2 × 24 GB Mac M3 · 24 GB Mac M4 Max · 64 GB
Licence
Size
$
680 models
#ModelParamsContextCommercial use30dOn RTX 4090 · 24 GB
251 Qwen3.8-4B-Distill-GGUF empero-ai · text-generation — — ✓ apache-2.0 793 K 3.6 GB
252 Qwen3-8B-FP8 Qwen · text-generation 8.2 B 41 K ✓ apache-2.0 780 K 12.1 GB
253 rorshark-vit-base amunchet · image-classification 90 M — ✓ apache-2.0 777 K 0.9 GB
254 Qwen3.8-2B-Distill-GGUF empero-ai · text-generation — — ✓ apache-2.0 772 K 1.9 GB
255 efficientnet_b0.ra_in1k timm · image-classification 10 M — ✓ apache-2.0 761 K 0.5 GB
256 yolos-small hustvl · object-detection 30 M — ✓ apache-2.0 760 K 0.6 GB
257 pythia-6.9b EleutherAI · text-generation 7.0 B 2 K ✓ apache-2.0 754 K 16.8 GB
258 nemotron-3.5-asr-streaming-0.6b nvidia · ASR 640 M — other 752 K 1.4 GB
259 gemma-2-9b-it google · text-generation · gated 9.2 B — ⚠ gemma 745 K 22.2 GB
260 VibeVoice-ASR microsoft · ASR 8.7 B — ✓ mit 738 K 20.9 GB
261 LaBSE sentence-transformers · sentence-similarity 470 M 512 ✓ apache-2.0 734 K 2.6 GB
262 bloomz-560m bigscience · text-generation 560 M — ⚠ bigscience-bloom-rail-1.0 724 K 1.8 GB
263 Kokoro-82M-v1.0-ONNX onnx-community · text-to-speech 82 M — ✓ apache-2.0 720 K 0.7 GB
264 ast-finetuned-audioset-10-10-0.4593 MIT · audio-classification 90 M — ✓ bsd-3-clause 719 K 0.9 GB
265 deepseek-coder-7b-instruct-v1.5 deepseek-ai · text-generation 6.9 B 4 K other 718 K 16.7 GB
266 Qwen3-14B-NVFP4 nvidia · text-generation 8.2 B 41 K ✓ apache-2.0 713 K 13.3 GB
267 wav2vec2-large-robust-12-ft-emotion-msp-dim audeering · audio-classification 170 M — ✗ cc-by-nc-sa-4.0 713 K 1.3 GB
268 Qwen2-0.5B Qwen · text-generation 490 M 131 K ✓ apache-2.0 709 K 1.7 GB
269 resnet50.ram_in1k timm · image-classification 30 M — ✓ apache-2.0 709 K 0.6 GB
270 gemma-4-12B-agentic-fable5-composer2.5-v2-3.5x-tau2-GGUF yuxinlu1 · text-generation — — ✓ apache-2.0 708 K 1.4 GB
271 Qwen2.5-Coder-7B Qwen · text-generation 7.6 B 33 K ✓ apache-2.0 706 K 18.4 GB
272 e5-base intfloat · sentence-similarity 110 M 512 ✓ mit 701 K 1.0 GB
273 Qwen3.8-27B-DFlash2-GGUF z-lab · text-generation — — ✓ apache-2.0 696 K 1.8 GB
274 Giga-Embeddings-instruct ai-sage · feature-extraction 3.5 B — ✓ mit 695 K 16.2 GB
275 Qwen3.8-9B-Distill-GGUF empero-ai · text-generation — — ✓ apache-2.0 693 K 6.9 GB
276 bert-base-multilingual-uncased-sentiment nlptown · text-classification 170 M 512 ✓ mit 689 K 1.3 GB
277 Qwen2.5-7B Qwen · text-generation 7.6 B 131 K ✓ apache-2.0 687 K 18.4 GB
278 LaBSE setu4993 · sentence-similarity 471 M 512 ✓ apache-2.0 687 K 2.6 GB
279 wav2vec2-large-xlsr-53-gender-recognition-librispeech alefiury · audio-classification 320 M — ✓ apache-2.0 676 K 1.9 GB
280 paraphrase-multilingual-MiniLM-L12-v2 Xenova · feature-extraction 120 M 512 unknown 675 K 0.8 GB
281 wikineural-multilingual-ner Babelscape · token-classification 180 M 512 ✗ cc-by-nc-sa-4.0 675 K 1.3 GB
282 parakeet-ctc-1.1b nvidia · ASR 1.1 B — ✓ cc-by-4.0 672 K 2.0 GB
283 paraphrase-MiniLM-L3-v2 sentence-transformers · sentence-similarity 20 M 512 ✓ apache-2.0 668 K 0.6 GB
284 gte-Qwen2-1.5B-instruct Alibaba-NLP · sentence-similarity 1.8 B 131 K ✓ apache-2.0 665 K 8.6 GB
285 gemma-2-2b-it google · text-generation · gated 2.6 B — ⚠ gemma 663 K 6.6 GB
286 Ternary-Bonsai-27B-gguf prism-ml · text-generation — — ✓ apache-2.0 663 K 1.2 GB
287 Qwen3-TTS-12Hz-0.6B-Base Qwen · text-to-speech 910 M — ✓ apache-2.0 655 K 3.4 GB
288 stable-diffusion-v1-4 CompVis · text-to-image 860 M — ⚠ creativeml-openrail-m 650 K 13.5 GB
289 audiobox-aesthetics facebook · audio-classification 100 M — ✓ cc-by-4.0 637 K 1.0 GB
290 nli-mpnet-base-v2 sentence-transformers · sentence-similarity 110 M 512 ✓ apache-2.0 635 K 1.0 GB
291 Nemotron-3-Embed-1B-BF16 nvidia · sentence-similarity 1.1 B 262 K other 633 K 3.2 GB
292 all-roberta-large-v1 sentence-transformers · sentence-similarity 360 M 512 ✓ apache-2.0 632 K 2.1 GB
293 Qwen2.5-Coder-7B-Instruct-AWQ Orion-zhen · text-generation 7.6 B 33 K ✓ apache-2.0 623 K 7.9 GB
294 RMBG-2.0 briaai · image-segmentation · gated 220 M — other 622 K 1.5 GB
295 MiniCPM-SALA-AWQ-8bit cyankiwi · text-generation 3.1 B 524 K ✓ apache-2.0 616 K 12.7 GB
296 gte-large thenlper · sentence-similarity 340 M 512 ✓ mit 616 K 1.3 GB
297 SmolLM3-3B-Base HuggingFaceTB · text-generation 3.1 B 66 K ✓ apache-2.0 615 K 7.7 GB
298 SmolLM3-3B HuggingFaceTB · text-generation 3.1 B 66 K ✓ apache-2.0 614 K 7.7 GB
299 EXAONE-3.5-7.8B-Instruct-AWQ LGAI-EXAONE · text-generation 7.8 B 33 K other 614 K 7.5 GB
300 MiniCPM5-1B openbmb · text-generation 1.1 B 131 K ✓ apache-2.0 611 K 3.0 GB
VRAM figures are estimates for the smallest available quantization at 8K context — see /methodology. Downloads refresh nightly from the Hugging Face API.