AImodelsComparison.com 1,213 open · 210 API
Menu
Models Best of Trending Can I run it? Methodology MCP server About
1,423 models · 1,213 open weights · 210 API-only · refreshed nightly

Models that run on RTX 4090 · 24 GB

Every model in the catalog — open weights you can self-host and API-only models — with licence or API price, estimated VRAM and daily-tracked downloads. Filters update the URL — share any view.

Type
All 1,423 Open weights (self-host) 1,213 API-only 210
Task
All text-generation 735 text-to-image 165 image-text-to-text 110 ASR 82 sentence-similarity 63 text-classification 50 translation 50 feature-extraction 46 image-classification 41 text-to-speech 23 token-classification 22 summarization 9 audio-classification 9 image-segmentation 9 object-detection 7 audio-text-to-text 1 any-to-any 1
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
$
762 models
#ModelParamsContextCommercial use30dOn RTX 4090 · 24 GB
101 DeepSeek-OCR deepseek-ai · image-text-to-text Open weights 3.3 B 8 K ✓ mit 2.0 M 8.3 GB
102 resnet18.a1_in1k timm · image-classification Open weights 10 M — ✓ apache-2.0 2.0 M 0.6 GB
103 gte-large-en-v1.5 Alibaba-NLP · sentence-similarity Open weights 430 M 8 K ✓ apache-2.0 1.9 M 2.5 GB
104 ast-finetuned-audioset-10-10-0.4593 MIT · audio-classification Open weights 90 M — ✓ bsd-3-clause 1.9 M 0.9 GB
105 Qwen3-VL-8B-Instruct-GGUF Qwen · image-text-to-text Open weights 8.0 B — ✓ apache-2.0 1.9 M 7.2 GB
106 NVIDIA-Nemotron-3-Nano-4B-BF16 nvidia · text-generation Open weights 4.0 B 262 K other 1.9 M 9.8 GB
107 paraphrase-mpnet-base-v2 sentence-transformers · sentence-similarity Open weights 110 M 512 ✓ apache-2.0 1.9 M 1.0 GB
108 Qwen3.5-9B-GGUF unsloth · image-text-to-text Open weights — — ✓ apache-2.0 1.8 M 5.2 GB
109 wav2vec2-base-960h facebook · ASR Open weights 90 M — ✓ apache-2.0 1.8 M 0.9 GB
110 SmolVLM2-500M-Video-Instruct HuggingFaceTB · image-text-to-text Open weights 510 M — ✓ apache-2.0 1.8 M 2.8 GB
111 Qwen3-14B-AWQ Qwen · text-generation Open weights 14.8 B 41 K ✓ apache-2.0 1.8 M 13.7 GB
112 multilingual-e5-large-instruct intfloat · feature-extraction Open weights 560 M 512 ✓ mit 1.7 M 1.8 GB
113 Gemma-4-26B-A4B-NVFP4 nvidia · text-generation Open weights 14.4 B — ✓ apache-2.0 1.7 M 23.3 GB
114 Qwen2.5-VL-3B-Instruct Qwen · image-text-to-text Open weights 3.8 B 128 K unknown 1.7 M 9.3 GB
115 Qwen3-ASR-1.7B Qwen · ASR Open weights 2.4 B — ✓ apache-2.0 1.7 M 6.0 GB
116 Prompt-Guard-86M meta-llama · text-classification · gated Open weights 280 M — ⚠ llama3.1 1.7 M 1.8 GB
117 distiluse-base-multilingual-cased-v1 sentence-transformers · sentence-similarity Open weights 130 M 512 ✓ apache-2.0 1.7 M 1.1 GB
118 resnet50.a1_in1k timm · image-classification Open weights 30 M — ✓ apache-2.0 1.6 M 0.6 GB
119 Qwen2.5-7B-Instruct-AWQ Qwen · text-generation Open weights 7.6 B 33 K ✓ apache-2.0 1.6 M 7.8 GB
120 Ternary-Bonsai-2-27B-gguf prism-ml · text-generation Open weights Also via API 27.0 B — ✓ apache-2.0 1.6 M 5.2 GB
121 Qwen3.6-35B-A3B-GGUF unsloth · image-text-to-text Open weights — — ✓ apache-2.0 1.6 M 11.6 GB
122 nsfw_image_detection Falconsai · image-classification Open weights 90 M — ✓ apache-2.0 1.6 M 0.9 GB
123 Qwen-Image-2.1-GGUF unsloth · text-to-image Open weights 7.1 B — other 1.6 M 4.3 GB
124 Qwen3-8B-AWQ Qwen · text-generation Open weights 8.2 B 41 K ✓ apache-2.0 1.6 M 8.4 GB
125 Swift-1.5-Qwen3.8-27B-GSQ-RCO-GGUF ukisai · text-generation Open weights 27.0 B — other 1.6 M 4.6 GB
126 kokoro-inno-clone-tuner remsky · text-to-speech Open weights 9.7 M — ✓ apache-2.0 1.6 M 0.5 GB
127 Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NEO-CODER-MAX-MTP-GGUF DavidAU · image-text-to-text Open weights 27.0 B — ✓ apache-2.0 1.5 M 17.9 GB
128 Qwen3.5-4B-GGUF unsloth · image-text-to-text Open weights — — ✓ apache-2.0 1.5 M 2.8 GB
129 paraphrase-MiniLM-L6-v2 sentence-transformers · sentence-similarity Open weights 20 M 512 ✓ apache-2.0 1.5 M 0.6 GB
130 Qwen3-VL-8B-Instruct-FP8 Qwen · image-text-to-text Open weights 8.8 B — ✓ apache-2.0 1.5 M 13.5 GB
131 Ornith-1.0-35B-GGUF ornith-ai · text-generation Open weights — — ✓ mit 1.5 M 23.8 GB
132 Qwen3-4B-Instruct-2507-FP8 Qwen · text-generation Open weights 4.4 B 262 K ✓ apache-2.0 1.5 M 6.9 GB
133 distilgpt2 distilbert · text-generation Open weights 90 M — ✓ apache-2.0 1.5 M 0.9 GB
134 jina-embeddings-v3 jinaai · feature-extraction Open weights 570 M 8 K ✗ cc-by-nc-4.0 1.5 M 1.8 GB
135 multi-qa-mpnet-base-dot-v1 sentence-transformers · sentence-similarity Open weights 110 M 512 unknown 1.5 M 1.0 GB
136 Mistral-7B-Instruct-v0.2 mistralai · text-generation Open weights 7.2 B 33 K ✓ apache-2.0 1.5 M 17.5 GB
137 Voxtral-Mini-4B-Realtime-2602 mistralai · ASR Open weights 4.4 B — ✓ apache-2.0 1.5 M 20.7 GB
138 SapBERT-from-PubMedBERT-fulltext cambridgeltl · feature-extraction Open weights 110 M 512 ✓ apache-2.0 1.4 M 1.0 GB
139 Qwen3-TTS-12Hz-1.7B-CustomVoice Qwen · text-to-speech Open weights 1.9 B — ✓ apache-2.0 1.4 M 5.8 GB
140 Dirk-Qwen3.8-27B-GGUF peculiar-ragdoll · image-text-to-text Open weights 27.0 B — ✓ apache-2.0 1.4 M 14.2 GB
141 chandra-ocr-2 datalab-to · image-text-to-text Open weights 5.3 B — ⚠ openrail 1.4 M 12.9 GB
142 Qwen2.5-3B-Instruct-AWQ Qwen · text-generation Open weights 3.4 B 33 K other 1.4 M 4.0 GB
143 wav2vec2-xls-r-300m-cs-250 comodoro · ASR Open weights 320 M — ✓ apache-2.0 1.4 M 1.9 GB
144 rtdetr_r101vd_coco_o365 PekingU · object-detection Open weights 80 M — ✓ apache-2.0 1.4 M 0.9 GB
145 Qwen3.8-27B-GSQ-RCO-GGUF ISTA-DASLab · image-text-to-text Open weights — — ✓ apache-2.0 1.4 M 1.5 GB
146 Qwen-Image-2.1-Turbo-GGUF unsloth · text-to-image Open weights — — other 1.4 M 3.2 GB
147 gender-classification rizvandwiki · image-classification Open weights 90 M — unknown 1.3 M 0.9 GB
148 Qwen3.8-35B-A3B-Distill-GGUF empero-ai · text-generation Open weights 35.0 B — ✓ apache-2.0 1.3 M 19.6 GB
149 Llama-3.2-1B-Instruct meta-llama · text-generation · gated Open weights Also via API 1.2 B — ⚠ llama3.2 1.3 M 3.4 GB
150 ko-sroberta-multitask jhgan · sentence-similarity Open weights 110 M 512 unknown 1.3 M 1.0 GB
VRAM figures are estimates for the smallest available quantization at 8K context — see /methodology. Downloads refresh nightly from the Hugging Face API; API prices (blended 3:1 input:output per 1M tokens) and Artificial Analysis indices from OpenRouter.