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 2 × 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 88 image-text-to-text 80 sentence-similarity 55 feature-extraction 45 translation 43 text-classification 39 image-classification 32 token-classification 21 text-to-speech 12 audio-classification 10 object-detection 10 image-segmentation 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
$
763 models
#ModelParamsContextCommercial use30dOn 2 × 24 GB
451 Phi-3-mini-4k-instruct microsoft · text-generation 3.8 B 4 K ✓ mit 407 K 9.5 GB
452 Qwen3-8B-GGUF Qwen · text-generation — — ✓ apache-2.0 404 K 6.0 GB
453 gemma-2-9b-it-AWQ-INT4 hugging-quants · text-generation 9.2 B 8 K ⚠ gemma 402 K 8.7 GB
454 Qwen2.5-VL-7B-Instruct-NVFP4 nvidia · text-generation 5.0 B 128 K other 399 K 9.2 GB
455 EXAONE-3.5-7.8B-Instruct LGAI-EXAONE · text-generation 7.8 B 33 K other 396 K 36.1 GB
456 jina-reranker-m0 jinaai · text-classification 2.4 B 33 K ✗ cc-by-nc-4.0 395 K 6.2 GB
457 gemma-3-270m google · text-generation · gated 270 M — ⚠ gemma 395 K 1.1 GB
458 granite-4.1-3b ibm-granite · text-generation 3.4 B 131 K ✓ apache-2.0 393 K 8.5 GB
459 Ternary-Bonsai-8B-gguf prism-ml · text-generation — — ✓ apache-2.0 392 K 2.9 GB
460 Qwen3.8-27B-DFlash2 incoai · text-generation 1.9 B 262 K ✓ apache-2.0 391 K 5.0 GB
461 Kwaipilot_KAT-Coder-V2.5-Dev-GGUF bartowski · text-generation — — ✓ apache-2.0 390 K 11.3 GB
462 Phi-4-mini-instruct microsoft · text-generation 3.8 B 131 K ✓ mit 384 K 9.5 GB
463 TwIL-LM3 webAI-Official · text-generation 3.1 B 66 K other 384 K 3.1 GB
464 NVIDIA-Nemotron-Nano-9B-v2 nvidia · text-generation 8.9 B 131 K other 383 K 21.4 GB
465 rtdetr_r50vd_coco_o365 PekingU · object-detection 40 M — ✓ apache-2.0 380 K 0.7 GB
466 falcon-7b tiiuae · text-generation 7.2 B — ✓ apache-2.0 379 K 17.5 GB
467 pythia-14m EleutherAI · text-generation 10 M 2 K ✓ apache-2.0 378 K 0.5 GB
468 Hermes-3-Llama-3.1-8B NousResearch · text-generation 8.0 B 131 K ⚠ llama3 377 K 19.4 GB
469 mistral-7b-v0.3-bnb-4bit unsloth · text-generation 7.5 B 33 K ✓ apache-2.0 377 K 6.2 GB
470 Ornith-1.5-9B-OBLITERATED OBLITERATUS · text-generation 9.7 B — ✓ mit 371 K 6.3 GB
471 Qwen2-7B-Instruct Qwen · text-generation 7.6 B 33 K ✓ apache-2.0 369 K 18.4 GB
472 segformer-b0-finetuned-ade-512-512 nvidia · image-segmentation <0.1 M — other 368 K 0.5 GB
473 Llama-3.2-3B meta-llama · text-generation · gated 3.2 B — ⚠ llama3.2 368 K 8.0 GB
474 Parable-Granite-4.1-3B-Claude-Fable-5-GGUF AnkitAI · text-generation — — ✓ apache-2.0 366 K 2.8 GB
475 privacy-filter-multilingual-GGUF LocalAI-io · token-classification — — ✓ apache-2.0 366 K 2.3 GB
476 Qwen3.8-27B-DFlash2 z-lab · text-generation 1.9 B 262 K ✓ apache-2.0 364 K 5.0 GB
477 Parable-Granite-4.1-8B-Claude-Fable-5-GGUF AnkitAI · text-generation — — ✓ apache-2.0 362 K 6.1 GB
478 Qwen2.5-Coder-1.5B Qwen · text-generation 1.5 B 33 K ✓ apache-2.0 361 K 4.1 GB
479 MiniCPM5-1B-Claude-Opus-Fable5-V2-Thinking-GGUF GnLOLot · text-generation — — ✓ apache-2.0 360 K 1.8 GB
480 Qwen3.6-35B-A3B-NVFP4-MTP-GGUF michaelw9999 · text-generation — — unknown 360 K 23.0 GB
481 POCKET-26B-GGUF FINAL-Bench · text-generation — — ✓ apache-2.0 360 K 12.7 GB
482 NVIDIA-Nemotron-3.5-Lightning-30B-A3B-FP8 RedHatAI · text-generation 31.6 B 262 K unknown 357 K 40.8 GB
483 Z-Image-Turbo-GGUF unsloth · text-to-image — — ✓ apache-2.0 356 K 4.5 GB
484 vlt5-base-keywords Voicelab · text-generation 280 M — ✓ cc-by-4.0 355 K 1.8 GB
485 t5-large google-t5 · translation 740 M — ✓ apache-2.0 352 K 3.9 GB
486 amd.Instella-MoE-16B-A3B-Think-GGUF DevQuasar · text-generation — — unknown 351 K 7.7 GB
487 RMBG-1.4 briaai · image-segmentation 40 M — other 349 K 0.7 GB
488 wide_resnet50_2.racm_in1k timm · image-classification 70 M — ✓ apache-2.0 348 K 0.8 GB
489 animagine-xl-4.0 cagliostrolab · text-to-image 2.6 B — ⚠ openrail++ 344 K 23.8 GB
490 Agents-A1-4B InternScience · text-generation 4.5 B — ✓ apache-2.0 344 K 11.2 GB
491 Ling-3.0-flash-GGUF AtomicChat · text-generation — — ✓ mit 341 K 36.1 GB
492 Ornith-1.5-9B-MLX-8bit ornith-ai · text-generation 9.0 B — unknown 341 K 12.3 GB
493 Ornith-1.5-9B-MLX ornith-ai · text-generation 9.0 B — unknown 341 K 21.5 GB
494 RealVisXL_V5.0 SG161222 · text-to-image 2.6 B — ⚠ openrail++ 341 K 46.7 GB
495 Phi-3.5-mini-instruct microsoft · text-generation 3.8 B 131 K ✓ mit 341 K 9.5 GB
496 DeepSeek-R1-Distill-Qwen-14B deepseek-ai · text-generation 14.8 B 131 K ✓ mit 340 K 35.2 GB
497 sd-turbo stabilityai · text-to-image 870 M — unknown 339 K 14.9 GB
498 Qwen2.5-3B Qwen · text-generation 3.1 B 33 K other 338 K 7.8 GB
499 Qwopus3.6-27B-Fusion-GGUF KyleHessling1 · text-generation — — other 337 K 15.4 GB
500 nsfw_image_detector Freepik · image-classification 90 M — ✓ mit 334 K 0.7 GB
VRAM figures are estimates for the smallest available quantization at 8K context — see /methodology. Downloads refresh nightly from the Hugging Face API.