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
51 indonesian-roberta-base-posp-tagger w11wo · token-classification Open weights 120 M 512 ✓ mit 3.6 M 1.1 GB
52 snowflake-arctic-embed-l-v2.0 Snowflake · sentence-similarity Open weights 570 M 8 K ✓ apache-2.0 3.6 M 3.1 GB
53 Qwen3.5-0.8B Qwen · image-text-to-text Open weights 870 M — ✓ apache-2.0 3.5 M 2.6 GB
54 OmniVoice k2-fsa · text-to-speech Open weights 610 M — unknown 3.5 M 4.2 GB
55 whisper-large-v3 openai · ASR Open weights 1.5 B — ✓ apache-2.0 3.5 M 10.9 GB
56 pythia-160m EleutherAI · text-generation Open weights 210 M 2 K ✓ apache-2.0 3.5 M 0.9 GB
57 Bangla-twoclass-Sentiment-Analyzer Arunavaonly · text-classification Open weights 280 M 512 ✓ mit 3.4 M 1.8 GB
58 Qwen3.8-27B-iMatrix-NVFP4-MTP-GGUF cdiamond · image-text-to-text Open weights — — ✓ apache-2.0 3.3 M 19.3 GB
59 finbert ProsusAI · text-classification Open weights 110 M 512 ✗ cc-by-nc-sa-4.0 3.3 M 1.0 GB
60 OTel-2.0-Decision-26B-A4B-4bit farbodtavakkoli · text-generation Open weights 25.8 B — ✓ apache-2.0 3.2 M 22.8 GB
61 bge-small-zh-v1.5 BAAI · feature-extraction Open weights 20 M 512 ✓ mit 3.1 M 0.6 GB
62 Tiel-Coder-35B-A3B-GGUF-MTP peculiar-ragdoll · image-text-to-text Open weights 35.0 B — ✓ mit 3.1 M 19.7 GB
63 Qwen3.8-27B-MLX-4bit lmstudio-community · image-text-to-text Open weights 4.7 B — ✓ apache-2.0 3.0 M 18.9 GB
64 distilbert-base-uncased-finetuned-sst-2-english distilbert · text-classification Open weights 70 M 512 ✓ apache-2.0 2.9 M 0.8 GB
65 bge-base-en-v1.5-course-recommender-v5 datasocietyco · sentence-similarity Open weights 110 M 512 unknown 2.9 M 1.0 GB
66 Qwen3.8-27B-MLX-5bit lmstudio-community · image-text-to-text Open weights 5.5 B — ✓ apache-2.0 2.9 M 22.7 GB
67 t5-base google-t5 · translation Open weights 220 M — ✓ apache-2.0 2.8 M 1.5 GB
68 parakeet-tdt-0.6b-v3 mlx-community · ASR Open weights 630 M — ✓ cc-by-4.0 2.7 M 3.4 GB
69 bge-base-en BAAI · feature-extraction Open weights 110 M 512 ✓ mit 2.7 M 1.0 GB
70 Qwen2.5-3B-Instruct Qwen · text-generation Open weights 3.1 B 33 K other 2.6 M 7.8 GB
71 Qwen3-4B-Instruct-2507 Qwen · text-generation Open weights 4.0 B 262 K ✓ apache-2.0 2.6 M 10.0 GB
72 SmolLM2-135M HuggingFaceTB · text-generation Open weights 130 M 8 K ✓ apache-2.0 2.5 M 0.8 GB
73 bge-base-en-v1.5 Xenova · feature-extraction Open weights 110 M 512 ✓ mit 2.5 M 0.8 GB
74 Qwen-Image-2.1-Uncensored-Quantized abenzerps · text-to-image Open weights 7.1 B — other 2.5 M 6.1 GB
75 Qwen3-Embedding-4B Qwen · feature-extraction Open weights 4.0 B 41 K ✓ apache-2.0 2.5 M 10.0 GB
76 all-distilroberta-v1 sentence-transformers · sentence-similarity Open weights 80 M 512 ✓ apache-2.0 2.5 M 0.9 GB
77 Qwen3.8-27B-Uncensored-GGUF JonathanColetti · text-generation Open weights — — ✓ apache-2.0 2.5 M 1.5 GB
78 gemma-4-12b-it-GGUF unsloth · image-text-to-text Open weights 12.0 B — ✓ apache-2.0 2.5 M 7.9 GB
79 all-MiniLM-L12-v2 sentence-transformers · sentence-similarity Open weights 30 M 512 ✓ apache-2.0 2.5 M 0.7 GB
80 mms-300m-1130-forced-aligner MahmoudAshraf · ASR Open weights 320 M — ✗ cc-by-nc-4.0 2.4 M 1.9 GB
81 chatterbox ResembleAI · text-to-speech Open weights — — ✓ mit 2.4 M 12.2 GB
82 Ornith-1.0-9B deepreinforce-ai · text-generation Open weights <0.1 M — ✓ mit 2.4 M 21.2 GB
83 Ornith-1.0-9B-GGUF ornith-ai · text-generation Open weights — — ✓ mit 2.4 M 6.7 GB
84 bge-reranker-base BAAI · text-classification Open weights 280 M 512 ✓ mit 2.4 M 1.8 GB
85 wav2vec2-large-robust-24-ft-age-gender audeering · audio-classification Open weights 320 M — ✗ cc-by-nc-sa-4.0 2.4 M 1.9 GB
86 Qwen3-Embedding-8B Qwen · feature-extraction Open weights 7.6 B 41 K ✓ apache-2.0 2.4 M 18.3 GB
87 parakeet-unified-en-0.6b-gguf handy-computer · ASR Open weights 600 M — other 2.4 M 1.1 GB
88 gte-small thenlper · sentence-similarity Open weights 30 M 512 ✓ mit 2.3 M 0.6 GB
89 moondream2 vikhyatk · image-text-to-text Open weights 1.9 B — ✓ apache-2.0 2.3 M 5.0 GB
90 mxbai-embed-large-v1 mixedbread-ai · feature-extraction Open weights 340 M 512 ✓ apache-2.0 2.3 M 1.3 GB
91 Qwen3.8-27B-Uncensored-HauhauCS-Aggressive-MTP-GGUF HauhauCS · image-text-to-text Open weights — — ✓ apache-2.0 2.2 M 1.5 GB
92 Qwen-Image-2.1-Uncensored-GGUF abenzerps · text-to-image Open weights 7.1 B — other 2.2 M 6.1 GB
93 Qwen3.6-35B-A3B-MTP-GGUF unsloth · image-text-to-text Open weights — — ✓ apache-2.0 2.1 M 13.0 GB
94 Qwen3.8-27B-GGUF byteshape · image-text-to-text Open weights 27.0 B — ✓ apache-2.0 2.1 M 5.6 GB
95 Qwen3.5-9B-The-Defiant-Fable-Uncensored-Heretic-NEO-IMATRIX-MAX-MTP-GGUF DavidAU · image-text-to-text Open weights 9.0 B — ✓ apache-2.0 2.1 M 7.3 GB
96 VieNeu-TTS-v3-Turbo pnnbao-ump · text-to-speech Open weights 131 M 1 K ✓ apache-2.0 2.1 M 0.7 GB
97 nemotron-3.5-asr-streaming-0.6b-gguf handy-computer · ASR Open weights 600 M — other 2.0 M 1.1 GB
98 bge-reranker-large BAAI · feature-extraction Open weights 560 M 512 ✓ mit 2.0 M 3.0 GB
99 gemma-4-26B-A4B-it-GGUF unsloth · image-text-to-text Open weights — — ✓ apache-2.0 2.0 M 11.4 GB
100 GLM-OCR zai-org · image-text-to-text Open weights 1.3 B — ✓ mit 2.0 M 3.6 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.