AImodelsComparison.com 1,115 models
Menu
Models Best of Trending Can I run it? Methodology About
1,115 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 448 text-to-image 152 ASR 92 image-text-to-text 92 sentence-similarity 63 translation 52 feature-extraction 47 text-classification 45 image-classification 38 token-classification 26 text-to-speech 19 audio-classification 13 image-segmentation 10 summarization 9 object-detection 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
$
748 models
#ModelParamsContextCommercial use30dOn RTX 4090 · 24 GB
01 all-MiniLM-L6-v2 sentence-transformers · sentence-similarity 20 M 512 ✓ apache-2.0 218.1 M 0.6 GB
02 bge-small-en-v1.5 BAAI · feature-extraction 30 M 512 ✓ mit 59.4 M 0.7 GB
03 paraphrase-multilingual-MiniLM-L12-v2 sentence-transformers · sentence-similarity 120 M 512 ✓ apache-2.0 47.2 M 1.0 GB
04 Qwen3-0.6B Qwen · text-generation 750 M 41 K ✓ apache-2.0 30.5 M 2.3 GB
05 t5-small google-t5 · translation 60 M — ✓ apache-2.0 23.8 M 0.8 GB
06 mobilenetv3_small_100.lamb_in1k timm · image-classification <0.1 M — ✓ apache-2.0 21.5 M 0.5 GB
07 all-mpnet-base-v2 sentence-transformers · sentence-similarity 110 M 512 ✓ apache-2.0 18.1 M 1.0 GB
08 gpt2 openai-community · text-generation 140 M — ✓ mit 16.0 M 1.1 GB
09 bge-reranker-v2-m3 BAAI · text-classification 570 M 8 K ✓ apache-2.0 15.9 M 3.1 GB
10 nomic-embed-text-v1.5 nomic-ai · sentence-similarity 140 M 2 K ✓ apache-2.0 13.1 M 1.1 GB
11 vit-base-patch16-224 google · image-classification 90 M — ✓ apache-2.0 12.8 M 0.9 GB
12 Qwen3-4B Qwen · text-generation 4.0 B 41 K ✓ apache-2.0 12.6 M 10.0 GB
13 locate-anything.cpp-gguf mudler · object-detection 3.8 B — other 12.3 M 6.3 GB
14 Kokoro-82M hexgrad · text-to-speech 82 M — ✓ apache-2.0 10.5 M 0.7 GB
15 bge-large-en-v1.5 BAAI · feature-extraction 340 M 512 ✓ mit 10.1 M 2.0 GB
16 multilingual-e5-small intfloat · sentence-similarity 120 M 512 ✓ mit 9.8 M 1.0 GB
17 Qwen3-8B Qwen · text-generation 8.2 B 41 K ✓ apache-2.0 9.7 M 19.7 GB
18 paraphrase-multilingual-mpnet-base-v2 sentence-transformers · sentence-similarity 280 M 512 ✓ apache-2.0 9.6 M 1.8 GB
19 bge-base-en-v1.5 BAAI · feature-extraction 110 M 512 ✓ mit 9.2 M 1.0 GB
20 Qwen3-Embedding-0.6B Qwen · feature-extraction 600 M 33 K ✓ apache-2.0 8.6 M 1.9 GB
21 Qwen3.5-9B Qwen · image-text-to-text 9.7 B — ✓ apache-2.0 8.5 M 23.2 GB
22 Qwen3.5-4B Qwen · image-text-to-text 4.7 B — ✓ apache-2.0 7.9 M 11.5 GB
23 clap-htsat-fused laion · audio-classification 150 M — ✓ apache-2.0 7.8 M 1.2 GB
24 Qwen3-VL-8B-Instruct Qwen · image-text-to-text 8.8 B — ✓ apache-2.0 7.4 M 21.1 GB
25 Qwen2.5-7B-Instruct Qwen · text-generation 7.6 B 33 K ✓ apache-2.0 7.4 M 18.4 GB
26 multilingual-e5-large intfloat · feature-extraction 560 M 512 ✓ mit 6.8 M 3.0 GB
27 multilingual-e5-base intfloat · sentence-similarity 280 M 512 ✓ mit 6.7 M 1.8 GB
28 Llama-3.2-1B-Instruct meta-llama · text-generation · gated 1.2 B — ⚠ llama3.2 6.4 M 3.4 GB
29 whisper-large-v3-turbo openai · ASR 810 M — ✓ mit 6.3 M 2.4 GB
30 Qwen2.5-0.5B-Instruct Qwen · text-generation 490 M 33 K ✓ apache-2.0 6.3 M 1.7 GB
31 audio.cpp-gguf audio-cpp · text-to-speech — — other 6.2 M 1.6 GB
32 Llama-3.1-8B-Instruct meta-llama · text-generation · gated 8.0 B — ⚠ llama3.1 6.0 M 19.4 GB
33 Qwen2.5-1.5B-Instruct Qwen · text-generation 1.5 B 33 K ✓ apache-2.0 6.0 M 4.1 GB
34 opt-125m facebook · text-generation 125 M 2 K other 5.9 M 0.8 GB
35 Kimi-K3-DSpark RadixArk · text-generation 2.3 B 1.0 M unknown 5.4 M 5.8 GB
36 granite-embedding-small-english-r2 ibm-granite · feature-extraction 50 M 8 K ✓ apache-2.0 5.3 M 0.6 GB
37 Qwen2.5-VL-7B-Instruct Qwen · image-text-to-text 8.3 B 128 K ✓ apache-2.0 5.1 M 20.0 GB
38 Ornith-1.5-9B-GGUF ornith-ai · text-generation — — ✓ mit 5.0 M 6.9 GB
39 Ornith-1.0-9B-GGUF deepreinforce-ai · text-generation — — ✓ mit 4.9 M 6.7 GB
40 Ternary-Bonsai-2-27B-gguf prism-ml · text-generation 27.0 B — ✓ apache-2.0 4.8 M 5.2 GB
41 all-MiniLM-L6-v2 Xenova · feature-extraction 20 M 512 ✓ apache-2.0 4.3 M 0.5 GB
42 Qwen2.5-3B-Instruct Qwen · text-generation 3.1 B 33 K other 4.3 M 7.8 GB
43 finbert ProsusAI · text-classification 110 M 512 ✗ cc-by-nc-sa-4.0 4.3 M 1.0 GB
44 roberta-base-go_emotions SamLowe · text-classification 120 M 512 ✓ mit 4.2 M 1.1 GB
45 bge-base-en-v1.5-course-recommender-v5 datasocietyco · sentence-similarity 110 M 512 unknown 4.1 M 1.0 GB
46 Qwen3.8-27B-MLX-4bit lmstudio-community · image-text-to-text 4.7 B — ✓ apache-2.0 4.1 M 18.9 GB
47 Qwen3-1.7B Qwen · text-generation 2.0 B 41 K ✓ apache-2.0 4.0 M 5.3 GB
48 bge-small-zh-v1.5 BAAI · feature-extraction 20 M 512 ✓ mit 3.9 M 0.6 GB
49 Qwen3.8-27B-MLX-5bit lmstudio-community · image-text-to-text 5.5 B — ✓ apache-2.0 3.9 M 22.7 GB
50 Ornith-1.0-35B-GGUF deepreinforce-ai · text-generation — — ✓ mit 3.8 M 23.8 GB
VRAM figures are estimates for the smallest available quantization at 8K context — see /methodology. Downloads refresh nightly from the Hugging Face API.