AImodelsComparison.com 1,011 models
Menu
Models Best of Trending Can I run it? Methodology About
1,011 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 89 image-text-to-text 82 sentence-similarity 55 feature-extraction 47 translation 44 text-classification 39 image-classification 32 token-classification 22 text-to-speech 16 audio-classification 12 image-segmentation 8 object-detection 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
$
649 models
#ModelParamsContextCommercial use30dOn RTX 4090 · 24 GB
51 granite-embedding-small-english-r2 ibm-granite · feature-extraction 50 M 8 K ✓ apache-2.0 3.8 M 0.6 GB
52 GLM-OCR zai-org · image-text-to-text 1.3 B — ✓ mit 3.8 M 3.6 GB
53 Ornith-1.0-35B-GGUF deepreinforce-ai · text-generation — — ✓ mit 3.8 M 23.8 GB
54 Ornith-1.0-35B-GGUF ornith-ai · text-generation — — ✓ mit 3.8 M 23.8 GB
55 gemma-4-26B-A4B-it-AWQ-4bit cyankiwi · image-text-to-text 26.6 B — ✓ apache-2.0 3.7 M 23.4 GB
56 distilbert-base-uncased-finetuned-sst-2-english distilbert · text-classification 70 M 512 ✓ apache-2.0 3.7 M 0.8 GB
57 all-MiniLM-L12-v2 sentence-transformers · sentence-similarity 30 M 512 ✓ apache-2.0 3.5 M 0.7 GB
58 Qwen3-Embedding-4B Qwen · feature-extraction 4.0 B 41 K ✓ apache-2.0 3.4 M 10.0 GB
59 Qwen3-Embedding-8B Qwen · feature-extraction 7.6 B 41 K ✓ apache-2.0 3.3 M 18.3 GB
60 jina-embeddings-v3 jinaai · feature-extraction 570 M 8 K ✗ cc-by-nc-4.0 3.2 M 1.8 GB
61 Qwen3-4B-Instruct-2507 Qwen · text-generation 4.0 B 262 K ✓ apache-2.0 3.2 M 10.0 GB
62 Qwen3-VL-8B-Instruct-FP8 Qwen · image-text-to-text 8.8 B — ✓ apache-2.0 3.2 M 13.5 GB
63 fairface_age_image_detection dima806 · image-classification 90 M — ✓ apache-2.0 3.2 M 2.4 GB
64 Qwen2-1.5B-Instruct Qwen · text-generation 1.5 B 33 K ✓ apache-2.0 3.2 M 4.1 GB
65 chandra-ocr-2 datalab-to · image-text-to-text 5.3 B — ⚠ openrail 3.2 M 12.9 GB
66 llava-1.5-7b-hf llava-hf · image-text-to-text 7.1 B — ⚠ llama2 3.1 M 17.1 GB
67 indonesian-roberta-base-posp-tagger w11wo · token-classification 120 M 512 ✓ mit 3.1 M 1.1 GB
68 Qwen3.5-0.8B Qwen · image-text-to-text 870 M — ✓ apache-2.0 3.1 M 2.6 GB
69 Qwen2-VL-2B-Instruct Qwen · image-text-to-text 2.2 B 33 K ✓ apache-2.0 3.0 M 5.7 GB
70 koelectra-small-v3-nsmc daekeun-ml · text-classification 10 M 512 ✓ mit 2.9 M 0.6 GB
71 Florence-2-base microsoft · image-text-to-text 230 M — ✓ mit 2.8 M 1.0 GB
72 resnet50.a1_in1k timm · image-classification 30 M — ✓ apache-2.0 2.8 M 0.6 GB
73 paraphrase-MiniLM-L6-v2 sentence-transformers · sentence-similarity 20 M 512 ✓ apache-2.0 2.8 M 0.6 GB
74 Unlimited-OCR baidu · image-text-to-text 3.3 B 33 K ✓ mit 2.7 M 8.3 GB
75 Qwen3.5-2B Qwen · image-text-to-text 2.3 B — ✓ apache-2.0 2.6 M 5.8 GB
76 distilgpt2 distilbert · text-generation 90 M — ✓ apache-2.0 2.6 M 0.9 GB
77 moondream2 vikhyatk · image-text-to-text 1.9 B — ✓ apache-2.0 2.6 M 5.0 GB
78 paraphrase-MiniLM-L3-v2 sentence-transformers · sentence-similarity 20 M 512 ✓ apache-2.0 2.6 M 0.6 GB
79 Bonsai-27B-gguf prism-ml · text-generation — — ✓ apache-2.0 2.6 M 1.2 GB
80 Qwen2.5-0.5B Qwen · text-generation 490 M 33 K ✓ apache-2.0 2.6 M 1.7 GB
81 e5-large-v2 intfloat · sentence-similarity 340 M 512 ✓ mit 2.6 M 2.0 GB
82 TinyLlama-1.1B-Chat-v1.0 TinyLlama · text-generation 1.1 B 2 K ✓ apache-2.0 2.5 M 3.1 GB
83 snowflake-arctic-embed-xs Snowflake · sentence-similarity 20 M 512 unknown 2.5 M 0.6 GB
84 Qwen2.5-14B-Instruct-AWQ Qwen · text-generation 14.8 B 33 K ✓ apache-2.0 2.5 M 13.7 GB
85 chatterbox ResembleAI · text-to-speech — — ✓ mit 2.5 M 12.2 GB
86 mms-300m-1130-forced-aligner MahmoudAshraf · ASR 320 M — ✗ cc-by-nc-4.0 2.5 M 1.9 GB
87 pythia-160m EleutherAI · text-generation 210 M 2 K ✓ apache-2.0 2.5 M 0.9 GB
88 bge-reranker-large BAAI · feature-extraction 560 M 512 ✓ mit 2.4 M 3.0 GB
89 Qwen3-14B-AWQ Qwen · text-generation 14.8 B 41 K ✓ apache-2.0 2.4 M 13.7 GB
90 Ornith-1.0-9B deepreinforce-ai · text-generation 0 M — ✓ mit 2.4 M 21.2 GB
91 Ornith-1.0-9B ornith-ai · text-generation 0 M — ✓ mit 2.4 M 21.2 GB
92 Qwen3-VL-Embedding-8B Qwen · sentence-similarity 8.1 B — ✓ apache-2.0 2.4 M 19.6 GB
93 DeepSeek-OCR deepseek-ai · image-text-to-text 3.3 B 8 K ✓ mit 2.3 M 8.3 GB
94 all-distilroberta-v1 sentence-transformers · sentence-similarity 80 M 512 ✓ apache-2.0 2.3 M 0.9 GB
95 Qwen3-TTS-12Hz-1.7B-CustomVoice Qwen · text-to-speech 1.9 B — ✓ apache-2.0 2.3 M 5.8 GB
96 multilingual-e5-large-instruct intfloat · feature-extraction 560 M 512 ✓ mit 2.3 M 1.8 GB
97 whisper-small openai · ASR 240 M — ✓ apache-2.0 2.3 M 1.6 GB
98 Voxtral-Mini-4B-Realtime-2602 mistralai · ASR 4.4 B — ✓ apache-2.0 2.3 M 20.7 GB
99 Qwen3-VL-2B-Instruct Qwen · image-text-to-text 2.1 B — ✓ apache-2.0 2.2 M 5.5 GB
100 gemma-3-270m google · text-generation · gated 270 M — ⚠ gemma 2.1 M 1.1 GB
VRAM figures are estimates for the smallest available quantization at 8K context — see /methodology. Downloads refresh nightly from the Hugging Face API.