AImodelsComparison.com 1,000 models
Menu
Models Best of Trending Can I run it? Methodology About
1,000 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 85 image-text-to-text 80 sentence-similarity 54 feature-extraction 46 translation 43 text-classification 39 image-classification 32 token-classification 21 text-to-speech 15 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
$
643 models
#ModelParamsContextCommercial use30dOn RTX 4090 · 24 GB
451 wav2vec2-large-robust-24-ft-age-gender audeering · audio-classification 320 M — ✗ cc-by-nc-sa-4.0 246 K 1.9 GB
452 pythia-410m EleutherAI · text-generation 510 M 2 K ✓ apache-2.0 244 K 1.6 GB
453 llama-160m JackFram · text-generation 160 M 2 K ✓ apache-2.0 243 K 1.2 GB
454 hubert-large-speech-emotion-recognition-russian-dusha-finetuned xbgoose · audio-classification 320 M — ✓ apache-2.0 243 K 1.9 GB
455 Phi-3-mini-128k-instruct microsoft · text-generation 3.8 B 131 K ✓ mit 242 K 9.5 GB
456 ai-image-detector-dev-deploy haywoodsloan · image-classification 200 M — unknown 241 K 2.2 GB
457 table-transformer-structure-recognition-v1.1-all microsoft · object-detection 30 M — ✓ mit 240 K 0.6 GB
458 Qwen3-8B-GGUF Qwen · text-generation — — ✓ apache-2.0 239 K 6.0 GB
459 tiny_starcoder_py bigcode · text-generation 160 M — bigcode-openrail-m 238 K 1.2 GB
460 Qwen2.5-3B-Instruct-AWQ Qwen · text-generation 3.4 B 33 K other 238 K 4.0 GB
461 Meta-Llama-3.1-8B-Instruct NousResearch · text-generation 8.0 B 131 K ⚠ llama3.1 238 K 19.4 GB
462 pythia-14m EleutherAI · text-generation 10 M 2 K ✓ apache-2.0 237 K 0.5 GB
463 Qwen2.5-Math-PRM-7B Qwen · text-classification 7.6 B 4 K other 237 K 18.4 GB
464 internlm2-1_8b-reward internlm · text-classification 1.7 B 33 K other 236 K 4.5 GB
465 convnext_base.fb_in22k_ft_in1k timm · image-classification 90 M — ✓ apache-2.0 236 K 0.9 GB
466 Qwen2.5-Coder-14B-Instruct-GPTQ-Int4 Qwen · text-generation 14.8 B 33 K ✓ apache-2.0 234 K 13.7 GB
467 layoutreader hantian · token-classification 360 M 514 ✗ cc-by-nc-sa-4.0 234 K 1.3 GB
468 gliner_multi-v2.1 urchade · token-classification 290 M — ✓ apache-2.0 234 K 1.8 GB
469 Llama-3.2-1B-Instruct-Q8_0-GGUF hugging-quants · text-generation — — unknown 233 K 2.0 GB
470 distilbert-NER dslim · token-classification 70 M 512 ✓ apache-2.0 231 K 0.8 GB
471 Phi-3-vision-128k-instruct microsoft · text-generation 4.2 B 131 K ✓ mit 231 K 10.2 GB
472 Nemotron-Labs-Diffusion-8B nvidia · text-generation 8.5 B 262 K other 228 K 20.6 GB
473 TinyLLama-v0 Maykeye · text-generation 0 M 2 K ✓ apache-2.0 226 K 0.5 GB
474 LFM2.5-1.2B-Instruct-GGUF LiquidAI · text-generation — — other 226 K 1.3 GB
475 Qwen2.5-14B-bnb-4bit unsloth · text-generation 15.2 B 131 K ✓ apache-2.0 224 K 13.7 GB
476 Qwen3.6-35B-A3B-DFlash z-lab · text-generation 390 M 262 K ✓ apache-2.0 224 K 1.4 GB
477 Qwen3-4B-GGUF MaziyarPanahi · text-generation — — unknown 223 K 2.3 GB
478 vlt5-base-keywords Voicelab · text-generation 280 M — ✓ cc-by-4.0 223 K 1.8 GB
479 gemma-4-12b-heretic-abliterated-GGUF culturerevolt · text-generation — — ✓ apache-2.0 219 K 0.7 GB
480 Gemma-4-E4B-DECKARD-HERETIC-NVFP4 AEON-7 · text-generation 6.2 B — ⚠ gemma 217 K 12.6 GB
481 Meta-Llama-3.1-8B-FP8 RedHatAI · text-generation 8.0 B 131 K ⚠ llama3.1 216 K 11.7 GB
482 Mistral-7B-Instruct-v0.1 mistralai · text-generation 7.2 B 33 K ✓ apache-2.0 216 K 17.5 GB
483 animagine-xl-4.0 cagliostrolab · text-to-image 2.6 B — ⚠ openrail++ 215 K 23.8 GB
484 dvine82-xl martineux · text-to-image 2.6 B — unknown 213 K 8.5 GB
485 SmolLM2-1.7B-Instruct HuggingFaceTB · text-generation 1.7 B 8 K ✓ apache-2.0 213 K 4.5 GB
486 Mistral-7B-Instruct-v0.3-AWQ solidrust · text-generation 7.3 B 33 K ✓ apache-2.0 212 K 6.2 GB
487 IP-Adapter-FaceID h94 · text-to-image — — unknown 210 K 1.5 GB
488 t5-large google-t5 · translation 740 M — ✓ apache-2.0 210 K 3.9 GB
489 Ornith-1.0-35B-GGUF unsloth · text-generation — — ✓ mit 203 K 12.1 GB
490 xflux_text_encoders XLabs-AI · text-generation 4.8 B — ✓ apache-2.0 203 K 11.7 GB
491 Qwen2.5-Coder-1.5B Qwen · text-generation 1.5 B 33 K ✓ apache-2.0 200 K 4.1 GB
492 gemma-1.1-2b-it google · text-generation · gated 2.5 B — ⚠ gemma 200 K 6.4 GB
493 DeepSeek-Coder-V2-Lite-Instruct-FP8 RedHatAI · text-generation 15.7 B 164 K other 200 K 20.6 GB
494 Qwen2.5-1.5B-Instruct-GGUF Qwen · text-generation — — ✓ apache-2.0 199 K 1.3 GB
495 Qwen1.5-0.5B-Chat Qwen · text-generation 620 M 33 K other 199 K 2.0 GB
496 aya-expanse-8b-AWQ Orion-zhen · text-generation 9.1 B 8 K gpl-3.0 198 K 10.5 GB
497 Qwen3-4B-Thinking-2507-FP8 Qwen · text-generation 4.4 B 262 K ✓ apache-2.0 197 K 6.9 GB
498 Qwen2.5-Coder-32B-Instruct-GGUF Qwen · text-generation — — ✓ apache-2.0 197 K 9.1 GB
499 PowerLM-3b ibm-research · text-generation 3.5 B 4 K ✓ apache-2.0 195 K 16.5 GB
500 OLMoE-1B-7B-0924 allenai · text-generation 6.9 B 4 K ✓ apache-2.0 192 K 16.8 GB
VRAM figures are estimates for the smallest available quantization at 8K context — see /methodology. Downloads refresh nightly from the Hugging Face API.