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
351 Nemotron-3-Embed-1B-BF16 nvidia · sentence-similarity 1.1 B 262 K other 456 K 3.2 GB
352 Phi-4-mini-instruct microsoft · text-generation 3.8 B 131 K ✓ mit 455 K 9.5 GB
353 Bangla-twoclass-Sentiment-Analyzer Arunavaonly · text-classification 280 M 512 ✓ mit 454 K 1.8 GB
354 paraphrase-MiniLM-L12-v2 sentence-transformers · sentence-similarity 30 M 512 ✓ apache-2.0 454 K 0.7 GB
355 S-PubMedBert-MedQuAD TimKond · sentence-similarity 110 M 512 ✓ mit 453 K 1.0 GB
356 Ternary-Bonsai-27B-mlx-2bit prism-ml · text-generation 2.6 B — ✓ apache-2.0 453 K 10.2 GB
357 Qwen3-8B-Base Qwen · text-generation 8.2 B 33 K ✓ apache-2.0 451 K 19.7 GB
358 Qwen2.5-3B-Instruct-unsloth-bnb-4bit unsloth · text-generation 3.2 B 33 K ✓ apache-2.0 449 K 3.6 GB
359 stable-diffusion-v1-4 CompVis · text-to-image 860 M — ⚠ creativeml-openrail-m 447 K 13.5 GB
360 Qwen3-TTS-12Hz-0.6B-Base Qwen · text-to-speech 910 M — ✓ apache-2.0 445 K 3.4 GB
361 Qwen3Guard-Gen-4B Qwen · text-generation 4.4 B 33 K ✓ apache-2.0 440 K 10.9 GB
362 Nemotron-Labs-Diffusion-8B-Base nvidia · text-generation 8.5 B 4 K other 434 K 20.5 GB
363 Olmo-3-7B-Instruct allenai · text-generation 7.3 B 66 K ✓ apache-2.0 434 K 17.7 GB
364 vit_tiny_r_s16_p8_224.augreg_in21k timm · image-classification 10 M — ✓ apache-2.0 432 K 0.5 GB
365 Qwen2.5-1.5B-apeach jason9693 · text-classification 1.5 B 131 K unknown 431 K 7.5 GB
366 Voxtral-Mini-4B-Realtime-2602-gguf handy-computer · ASR — — ✓ apache-2.0 430 K 3.6 GB
367 Zamba2-1.2B-instruct Zyphra · text-generation 1.2 B 4 K ✓ apache-2.0 429 K 6.0 GB
368 LLaDA-8B-Instruct GSAI-ML · text-generation 8.0 B — ✓ mit 429 K 19.3 GB
369 japanese-gpt-neox-small rinna · text-generation 200 M 2 K ✓ mit 428 K 1.3 GB
370 deid_roberta_i2b2 obi · token-classification 350 M 512 ✓ mit 423 K 2.1 GB
371 saiga_llama3_8b IlyaGusev · text-generation 8.0 B 8 K other 423 K 19.4 GB
372 gemma-2-9b-it google · text-generation · gated 9.2 B — ⚠ gemma 417 K 22.2 GB
373 rtdetr_r101vd_coco_o365 PekingU · object-detection 80 M — ✓ apache-2.0 416 K 0.9 GB
374 bert-small-pii-detection gravitee-io · token-classification 30 M 512 ✓ apache-2.0 416 K 0.6 GB
375 granite-speech-4.1-2b ibm-granite · ASR 2.3 B — ✓ apache-2.0 415 K 6.2 GB
376 Qwen3-14B-FP8 Qwen · text-generation 14.8 B 41 K ✓ apache-2.0 412 K 20.7 GB
377 Meta-Llama-3.1-8B-Instruct unsloth · text-generation 8.0 B 131 K ⚠ llama3.1 410 K 19.4 GB
378 Qwen3-ForcedAligner-0.6B Qwen · ASR 920 M — ✓ apache-2.0 407 K 2.7 GB
379 Qwen2.5-Coder-14B-Instruct-AWQ Qwen · text-generation 14.8 B 33 K ✓ apache-2.0 406 K 13.7 GB
380 audiobox-aesthetics facebook · audio-classification 100 M — ✓ cc-by-4.0 401 K 1.0 GB
381 multilingual-sentiment-analysis tabularisai · text-classification 140 M 512 ✗ cc-by-nc-4.0 399 K 1.1 GB
382 DeepSeek-R1-Distill-Llama-8B deepseek-ai · text-generation 8.0 B 131 K ✓ mit 395 K 19.4 GB
383 EXAONE-3.5-7.8B-Instruct-AWQ LGAI-EXAONE · text-generation 7.8 B 33 K other 389 K 7.5 GB
384 wav2vec2-large-xlsr-kazakh aismlv · ASR 320 M — ✓ apache-2.0 386 K 1.9 GB
385 Ilama-3.2-1B hmellor · text-generation 1.2 B 131 K unknown 381 K 6.1 GB
386 mistral-7b-v0.3-bnb-4bit unsloth · text-generation 7.5 B 33 K ✓ apache-2.0 380 K 6.2 GB
387 MOSS-TTS OpenMOSS-Team · text-to-speech 8.5 B — ✓ apache-2.0 375 K 20.5 GB
388 convnext_femto.d1_in1k timm · image-classification 10 M — ✓ apache-2.0 375 K 0.5 GB
389 higgs-tts-3-4b bosonai · text-to-speech 4.7 B — other 374 K 11.4 GB
390 gemma-4-12B-agentic-fable5-composer2.5-v2-3.5x-tau2-GGUF yuxinlu1 · text-generation — — ✓ apache-2.0 373 K 1.4 GB
391 VieNeu-TTS-v3-Turbo pnnbao-ump · text-to-speech 130 M 1 K ✓ apache-2.0 370 K 1.1 GB
392 s2-pro fishaudio · text-to-speech 4.6 B — other 368 K 11.2 GB
393 Fanar-1-9B-Instruct QCRI · text-generation 8.8 B 4 K ✓ apache-2.0 364 K 21.1 GB
394 whisper-medium openai · ASR 760 M — ✓ apache-2.0 364 K 4.0 GB
395 segformer-b0-finetuned-ade-512-512 nvidia · image-segmentation 0 M — other 364 K 0.5 GB
396 Apertus-8B-Instruct-2509 swiss-ai · text-generation 8.1 B 66 K ✓ apache-2.0 361 K 19.4 GB
397 CodeLlama-7b-hf codellama · text-generation 6.7 B 16 K ⚠ llama2 356 K 16.3 GB
398 gpt-oss-20b-MXFP4-Q8 mlx-community · text-generation 20.9 B 131 K ✓ apache-2.0 355 K 16.9 GB
399 gpt-neo-125m EleutherAI · text-generation 150 M 2 K ✓ mit 350 K 1.1 GB
400 gemma-3-270m-it google · text-generation · gated 270 M — ⚠ gemma 346 K 1.1 GB
VRAM figures are estimates for the smallest available quantization at 8K context — see /methodology. Downloads refresh nightly from the Hugging Face API.