AImodelsComparison.com 1,054 models
Menu
Models Best of Trending Can I run it? Methodology About
1,054 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 410 text-to-image 153 ASR 92 image-text-to-text 89 sentence-similarity 61 feature-extraction 47 translation 47 text-classification 42 image-classification 34 token-classification 27 text-to-speech 12 audio-classification 11 object-detection 11 summarization 9 image-segmentation 9
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
$
719 models
#ModelParamsContextCommercial use30dOn RTX 4090 · 24 GB
101 resnet18.a1_in1k timm · image-classification 10 M — ✓ apache-2.0 2.0 M 0.6 GB
102 jina-embeddings-v3 jinaai · feature-extraction 570 M 8 K ✗ cc-by-nc-4.0 2.0 M 1.8 GB
103 Qwen2.5-VL-7B-Instruct-AWQ Qwen · image-text-to-text 8.3 B 128 K ✓ apache-2.0 2.0 M 9.4 GB
104 GLM-OCR zai-org · image-text-to-text 1.3 B — ✓ mit 2.0 M 3.6 GB
105 deepseek-v4-gguf antirez · text-generation — — ✓ mit 2.0 M 4.7 GB
106 romanian-wav2vec2 gigant · ASR 320 M — ✓ apache-2.0 1.9 M 1.9 GB
107 Gemma-4-E4B-Uncensored-HauhauCS-Aggressive HauhauCS · image-text-to-text — — ⚠ gemma 1.9 M 5.4 GB
108 wav2vec2-large-voxrex-swedish KBLab · ASR 320 M — ✓ cc0-1.0 1.9 M 1.9 GB
109 moondream2 vikhyatk · image-text-to-text 1.9 B — ✓ apache-2.0 1.9 M 5.0 GB
110 Voxtral-Mini-4B-Realtime-2602 mistralai · ASR 4.4 B — ✓ apache-2.0 1.9 M 20.7 GB
111 stsb-bert-tiny-safetensors sentence-transformers-testing · sentence-similarity <0.1 M 512 unknown 1.9 M 0.5 GB
112 resnet50.a1_in1k timm · image-classification 30 M — ✓ apache-2.0 1.9 M 0.6 GB
113 chatterbox ResembleAI · text-to-speech — — ✓ mit 1.8 M 12.2 GB
114 Llama-3.2-3B-Instruct meta-llama · text-generation · gated 3.2 B — ⚠ llama3.2 1.8 M 8.0 GB
115 nemotron-3.5-asr-streaming-0.6b-gguf handy-computer · ASR — — other 1.8 M 1.0 GB
116 Qwen3.8-27B-Heretic-Abliterated-Uncensored-GGUF 0bserverx · text-generation — — ✓ apache-2.0 1.8 M 8.9 GB
117 parakeet-tdt-0.6b-v3 mlx-community · ASR 630 M — ✓ cc-by-4.0 1.8 M 3.4 GB
118 Gemma-4-26B-A4B-NVFP4 nvidia · text-generation 14.4 B — ✓ apache-2.0 1.8 M 23.3 GB
119 filipino-wav2vec2-l-xls-r-300m-official Khalsuu · ASR 300 M — ✓ apache-2.0 1.8 M 1.2 GB
120 gemma-3-4b-it google · image-text-to-text · gated 4.3 B — ⚠ gemma 1.8 M 10.6 GB
121 Qwen3-8B-AWQ Qwen · text-generation 8.2 B 41 K ✓ apache-2.0 1.8 M 8.4 GB
122 tf_efficientnetv2_s.in21k_ft_in1k timm · image-classification 20 M — ✓ apache-2.0 1.8 M 0.6 GB
123 Mistral-7B-Instruct-v0.2 mistralai · text-generation 7.2 B 33 K ✓ apache-2.0 1.8 M 17.5 GB
124 llava-1.5-7b-hf llava-hf · image-text-to-text 7.1 B — ⚠ llama2 1.8 M 17.1 GB
125 paraphrase-mpnet-base-v2 sentence-transformers · sentence-similarity 110 M 512 ✓ apache-2.0 1.7 M 1.0 GB
126 gemma-4-26B-A4B-it-AWQ-4bit cyankiwi · image-text-to-text 25.8 B — ✓ apache-2.0 1.7 M 23.3 GB
127 nomic-embed-text-v2-moe nomic-ai · sentence-similarity 480 M — ✓ apache-2.0 1.7 M 2.7 GB
128 wav2vec2-large-xls-r-300m-Urdu kingabzpro · ASR 320 M — ✓ apache-2.0 1.7 M 1.9 GB
129 whisper-tiny openai · ASR 40 M — ✓ apache-2.0 1.7 M 0.7 GB
130 Qwen2-VL-7B-Instruct-AWQ Qwen · image-text-to-text 8.3 B 33 K ✓ apache-2.0 1.6 M 9.4 GB
131 e5-large-v2 intfloat · sentence-similarity 340 M 512 ✓ mit 1.6 M 2.0 GB
132 Qwen2.5-0.5B Qwen · text-generation 490 M 33 K ✓ apache-2.0 1.6 M 1.7 GB
133 multilingual-e5-large-instruct intfloat · feature-extraction 560 M 512 ✓ mit 1.6 M 1.8 GB
134 multi-qa-mpnet-base-dot-v1 sentence-transformers · sentence-similarity 110 M 512 unknown 1.6 M 1.0 GB
135 whisper-base openai · ASR 70 M — ✓ apache-2.0 1.6 M 0.8 GB
136 parakeet-unified-en-0.6b-gguf handy-computer · ASR — — ✓ cc-by-4.0 1.6 M 1.0 GB
137 paraphrase-MiniLM-L6-v2 sentence-transformers · sentence-similarity 20 M 512 ✓ apache-2.0 1.5 M 0.6 GB
138 Qwen3-4B-Base Qwen · text-generation 4.0 B 33 K ✓ apache-2.0 1.5 M 10.0 GB
139 Qwen3.5-9B-GGUF unsloth · image-text-to-text — — ✓ apache-2.0 1.5 M 5.2 GB
140 Qwen3-1.7B-Base Qwen · text-generation 1.7 B 33 K ✓ apache-2.0 1.5 M 4.5 GB
141 Qwen3.8-Flash-Next-GGUF unsloth · image-text-to-text — — other 1.5 M 3.6 GB
142 SmolLM2-135M-Instruct HuggingFaceTB · text-generation 130 M 8 K ✓ apache-2.0 1.5 M 0.8 GB
143 Ternary-Bonsai-2-27B-gguf prism-ml · text-generation 27.0 B — ✓ apache-2.0 1.5 M 5.2 GB
144 koelectra-small-v3-nsmc daekeun-ml · text-classification 10 M 512 ✓ mit 1.5 M 0.6 GB
145 SapBERT-from-PubMedBERT-fulltext cambridgeltl · feature-extraction 110 M 512 ✓ apache-2.0 1.5 M 1.0 GB
146 OTel-LLM-E4B-IT farbodtavakkoli · text-generation 4.0 B — ✓ apache-2.0 1.5 M 9.9 GB
147 Qwen3.5-9B-The-Defiant-Fable-Uncensored-Heretic-NEO-IMATRIX-MAX-MTP-GGUF DavidAU · image-text-to-text — — ✓ apache-2.0 1.5 M 5.9 GB
148 wav2vec2-base-960h facebook · ASR 90 M — ✓ apache-2.0 1.5 M 0.9 GB
149 TinyLlama-1.1B-Chat-v1.0 TinyLlama · text-generation 1.1 B 2 K ✓ apache-2.0 1.5 M 3.1 GB
150 Ornith-1.5-397B-GGUF ornith-ai · text-generation — — ✓ mit 1.4 M 1.5 GB
VRAM figures are estimates for the smallest available quantization at 8K context — see /methodology. Downloads refresh nightly from the Hugging Face API.