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
101 DeepSeek-OCR-2 deepseek-ai · image-text-to-text 3.4 B 8 K ✓ apache-2.0 2.1 M 8.5 GB
102 embeddinggemma-300m google · sentence-similarity · gated 300 M — ⚠ gemma 2.1 M 1.9 GB
103 Meta-Llama-3-8B meta-llama · text-generation · gated 8.0 B — ⚠ llama3 2.1 M 19.4 GB
104 nemotron-3.5-asr-streaming-0.6b-gguf handy-computer · ASR — — other 2.0 M 1.0 GB
105 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
106 Qwen3-ASR-1.7B Qwen · ASR 2.4 B — ✓ apache-2.0 2.0 M 6.0 GB
107 whisper-tiny openai · ASR 40 M — ✓ apache-2.0 2.0 M 0.7 GB
108 Qwen2.5-Coder-7B-Instruct Qwen · text-generation 7.6 B 33 K ✓ apache-2.0 2.0 M 18.4 GB
109 SmolLM2-135M-Instruct HuggingFaceTB · text-generation 130 M 8 K ✓ apache-2.0 2.0 M 0.8 GB
110 multi-qa-mpnet-base-dot-v1 sentence-transformers · sentence-similarity 110 M 512 unknown 1.9 M 1.0 GB
111 Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive HauhauCS · image-text-to-text — — ✓ apache-2.0 1.9 M 13.3 GB
112 resnet18.a1_in1k timm · image-classification 10 M — ✓ apache-2.0 1.9 M 0.6 GB
113 parakeet-unified-en-0.6b-gguf handy-computer · ASR — — ✓ cc-by-4.0 1.9 M 1.0 GB
114 parakeet-tdt-0.6b-v2 mlx-community · ASR 620 M — ✓ cc-by-4.0 1.9 M 3.3 GB
115 parakeet-ctc-1.1b nvidia · ASR 1.1 B — ✓ cc-by-4.0 1.9 M 2.0 GB
116 PowerMoE-3b ibm-research · text-generation 3.4 B 4 K ✓ apache-2.0 1.8 M 15.9 GB
117 SmolLM2-135M HuggingFaceTB · text-generation 130 M 8 K ✓ apache-2.0 1.8 M 0.8 GB
118 gemma-3-4b-it google · image-text-to-text · gated 4.3 B — ⚠ gemma 1.8 M 10.6 GB
119 bge-base-en-v1.5-course-recommender-v5 datasocietyco · sentence-similarity 110 M 512 unknown 1.8 M 1.0 GB
120 ko-sroberta-multitask jhgan · sentence-similarity 110 M 512 unknown 1.8 M 1.0 GB
121 Meta-Llama-3-8B-Instruct meta-llama · text-generation · gated 8.0 B — ⚠ llama3 1.8 M 19.4 GB
122 Qwen2-VL-7B-Instruct-AWQ Qwen · image-text-to-text 8.3 B 33 K ✓ apache-2.0 1.8 M 9.4 GB
123 Llama-3.2-1B meta-llama · text-generation · gated 1.2 B — ⚠ llama3.2 1.8 M 3.4 GB
124 wav2vec2-base-960h facebook · ASR 90 M — ✓ apache-2.0 1.7 M 0.9 GB
125 stsb-bert-tiny-safetensors sentence-transformers-testing · sentence-similarity 0 M 512 unknown 1.7 M 0.5 GB
126 gte-large-en-v1.5 Alibaba-NLP · sentence-similarity 430 M 8 K ✓ apache-2.0 1.7 M 2.5 GB
127 diffusiongemma-26B-A4B-it-NVFP4 nvidia · text-generation 14.4 B — ✓ apache-2.0 1.7 M 23.4 GB
128 distil-large-v3 distil-whisper · ASR 760 M — ✓ mit 1.7 M 5.6 GB
129 DeepSeek-R1-0528-Qwen3-8B deepseek-ai · text-generation 8.2 B 131 K ✓ mit 1.7 M 19.7 GB
130 tf_efficientnetv2_s.in21k_ft_in1k timm · image-classification 20 M — ✓ apache-2.0 1.6 M 0.6 GB
131 Qwen3.6-27B-Fable-Fusion-711-Uncensored-Heretic-NM-DAU-NEO-MAX-MTP-GGUF DavidAU · image-text-to-text — — ✓ apache-2.0 1.6 M 13.8 GB
132 t5-base google-t5 · translation 220 M — ✓ apache-2.0 1.6 M 1.5 GB
133 SapBERT-from-PubMedBERT-fulltext cambridgeltl · feature-extraction 110 M 512 ✓ apache-2.0 1.6 M 1.0 GB
134 paraphrase-mpnet-base-v2 sentence-transformers · sentence-similarity 110 M 512 ✓ apache-2.0 1.6 M 1.0 GB
135 Qwen3-TTS-12Hz-0.6B-CustomVoice Qwen · text-to-speech 910 M — ✓ apache-2.0 1.6 M 3.4 GB
136 Qwen3-0.6B-FP8 Qwen · text-generation 750 M 41 K ✓ apache-2.0 1.6 M 1.8 GB
137 bge-small-en BAAI · feature-extraction 30 M 512 ✓ mit 1.6 M 0.7 GB
138 bart-large-cnn facebook · summarization 410 M 1 K ✓ mit 1.6 M 2.3 GB
139 gender-classification rizvandwiki · image-classification 90 M — unknown 1.5 M 0.9 GB
140 nomic-embed-text-v2-moe nomic-ai · sentence-similarity 480 M — ✓ apache-2.0 1.5 M 2.7 GB
141 Qwen2-VL-7B-Instruct Qwen · image-text-to-text 8.3 B 33 K ✓ apache-2.0 1.5 M 20.0 GB
142 Llama-3.1-8B meta-llama · text-generation · gated 8.0 B — ⚠ llama3.1 1.5 M 19.4 GB
143 OpenELM-1_1B-Instruct apple · text-generation 1.1 B — apple-amlr 1.5 M 3.0 GB
144 SmolLM-1.7B-Instruct-quantized.w4a16 nm-testing · text-generation 1.8 B 2 K ✓ apache-2.0 1.5 M 2.7 GB
145 Llama-3.2-1B-Instruct-FP8-dynamic RedHatAI · text-generation 1.5 B 131 K ⚠ llama3.2 1.5 M 3.0 GB
146 gpt2-large openai-community · text-generation 810 M — ✓ mit 1.5 M 4.2 GB
147 Gemma-4-26B-A4B-NVFP4 nvidia · text-generation 14.4 B — ✓ apache-2.0 1.5 M 23.3 GB
148 table-transformer-structure-recognition microsoft · object-detection 30 M 1 K ✓ mit 1.5 M 0.6 GB
149 Llama-3.2-3B-Instruct meta-llama · text-generation · gated 3.2 B — ⚠ llama3.2 1.5 M 8.0 GB
150 InternVL2-2B OpenGVLab · image-text-to-text 2.2 B — ✓ mit 1.5 M 5.7 GB
VRAM figures are estimates for the smallest available quantization at 8K context — see /methodology. Downloads refresh nightly from the Hugging Face API.