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 2 × 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
$
871 models
#ModelParamsContextCommercial use30dOn 2 × 24 GB
601 diffusiongemma-26B-A4B-it-NVFP4 nvidia · text-generation Open weights 14.4 B — ✓ apache-2.0 232 K 23.4 GB
602 resnet18.a3_in1k timm · image-classification Open weights 10 M — ✓ apache-2.0 231 K 0.6 GB
603 t5-3b google-t5 · translation Open weights 2.9 B — ✓ apache-2.0 230 K 13.5 GB
604 t5-large google-t5 · translation Open weights 740 M — ✓ apache-2.0 230 K 3.9 GB
605 h2ovl-mississippi-2b h2oai · text-generation Open weights 2.2 B — ✓ apache-2.0 230 K 5.6 GB
606 stable-diffusion-inpainting stable-diffusion-v1-5 · text-to-image Open weights — — ⚠ creativeml-openrail-m 229 K 3.5 GB
607 h2o-danube3-500m-chat h2oai · text-generation Open weights 514 M 8 K ✓ apache-2.0 229 K 1.7 GB
608 Llama-3.1-8B-Instruct-4bit mlx-community · text-generation Open weights 1.3 B 131 K ⚠ llama3.1 228 K 5.7 GB
609 GaMS3-12B-Instruct cjvt · text-generation Open weights 11.8 B 131 K ⚠ gemma 226 K 28.2 GB
610 ftrobertallm zhx123 · text-classification Open weights 355 M 512 ✓ mit 225 K 2.1 GB
611 prompt-saturation-attack-detector GuardrailsAI · text-classification Open weights 4.4 M 512 unknown 225 K 0.5 GB
612 Qwen3-8B-FP8 Qwen · text-generation Open weights 8.2 B 41 K ✓ apache-2.0 225 K 12.1 GB
613 Z-Image-GGUF unsloth · text-to-image Open weights 6.2 B — ✓ apache-2.0 224 K 4.0 GB
614 TinyStories-1M roneneldan · text-generation Open weights 1.0 M 2 K unknown 224 K 0.5 GB
615 Qwen3-14B-Base Qwen · text-generation Open weights 14.8 B 33 K ✓ apache-2.0 224 K 35.2 GB
616 RealVisXL_V4.0 SG161222 · text-to-image Open weights 2.6 B — ⚠ openrail++ 223 K 31.4 GB
617 Qwen3-32B-AWQ Qwen · text-generation Open weights 32.8 B 41 K ✓ apache-2.0 222 K 26.7 GB
618 OpenMed-NER-BloodCancerDetect-TinyMed-65M OpenMed · token-classification Open weights 65 M 512 ✓ apache-2.0 222 K 0.7 GB
619 OpenMed-NER-ChemicalDetect-ModernMed-149M OpenMed · token-classification Open weights 150 M 8 K ✓ apache-2.0 222 K 0.9 GB
620 LLaDA-8B-Instruct GSAI-ML · text-generation Open weights 8.0 B — ✓ mit 221 K 19.3 GB
621 long-t5-tglobal-base-sci-simplify pszemraj · summarization Open weights 248 M — ✓ apache-2.0 221 K 1.6 GB
622 GLM-4.7-Flash-AWQ-4bit cyankiwi · text-generation Open weights 32.1 B 203 K ✓ mit 221 K 27.5 GB
623 Olmo-3-7B-Instruct-SFT allenai · text-generation Open weights 7.3 B 66 K ✓ apache-2.0 220 K 17.7 GB
624 NVIDIA-Nemotron-3.5-Lightning-30B-A3B-GGUF ggml-org · text-generation Open weights 30.0 B 262 K other 220 K 25.8 GB
625 vlt5-base-keywords Voicelab · text-generation Open weights 280 M — ✓ cc-by-4.0 220 K 1.8 GB
626 Qwen3-0.6B-GGUF Qwen · text-generation Open weights 600 M 41 K ✓ apache-2.0 220 K 1.3 GB
627 OpenMed-NER-PharmaDetect-BigMed-278M OpenMed · token-classification Open weights 278 M 512 ✓ apache-2.0 219 K 1.2 GB
628 automotive flywheel-ai · text-generation Open weights 34.7 B — ✓ apache-2.0 219 K 29.0 GB
629 DeepSeek-R1-0528-Qwen3-8B-MLX-4bit lmstudio-community · text-generation Open weights 1.3 B 131 K ✓ mit 218 K 5.8 GB
630 Llama-3.1-Nemotron-Nano-8B-v1 nvidia · text-generation Open weights 8.0 B 131 K other 218 K 19.4 GB
631 Ornith-1.5-9B-MLX-6bit ornith-ai · text-generation Open weights 9.0 B — unknown 218 K 9.8 GB
632 SmolLM2-360M-Instruct HuggingFaceTB · text-generation Open weights 360 M 8 K ✓ apache-2.0 218 K 1.4 GB
633 Qwen2.5-Coder-14B-Instruct-AWQ Qwen · text-generation Open weights 14.8 B 33 K ✓ apache-2.0 216 K 13.7 GB
634 Gemma-4-E4B-DECKARD-HERETIC-NVFP4 AEON-7 · text-generation Open weights 6.2 B — ⚠ gemma 216 K 12.6 GB
635 TinyLLama-v0 Maykeye · text-generation Open weights <0.1 M 2 K ✓ apache-2.0 215 K 0.5 GB
636 qwen3-4b-base-dapo-v4 ReliquaryForge · text-generation Open weights 4.0 B 33 K ✓ apache-2.0 215 K 10.0 GB
637 Realistic_Vision_V5.1_noVAE SG161222 · text-to-image Open weights 860 M — ⚠ creativeml-openrail-m 215 K 19.4 GB
638 OpenMed-NER-DiseaseDetect-BioMed-335M OpenMed · token-classification Open weights 334 M 512 ✓ apache-2.0 214 K 1.3 GB
639 SmolLM3-3B-Base HuggingFaceTB · text-generation Open weights 3.1 B 66 K ✓ apache-2.0 213 K 7.7 GB
640 Parable-Qwen3-4B-Claude-Fable-5-GGUF AnkitAI · text-generation Open weights 4.0 B 41 K ✓ apache-2.0 213 K 3.8 GB
641 Parable-Qwen3-8B-Claude-Fable-5-GGUF AnkitAI · text-generation Open weights 8.0 B 41 K ✓ apache-2.0 212 K 7.2 GB
642 resnet-50 microsoft · image-classification Open weights 30 M — ✓ apache-2.0 212 K 0.6 GB
643 MiniCPM5-2B-MLX openbmb · text-generation Open weights 2.5 B 131 K ✓ apache-2.0 212 K 2.4 GB
644 wildguard allenai · text-generation · gated Open weights 7.3 B — ✓ apache-2.0 211 K 17.5 GB
645 Qwen3Guard-Gen-0.6B Qwen · text-generation Open weights 750 M 33 K ✓ apache-2.0 211 K 2.3 GB
646 Llama-2-7b-hf meta-llama · text-generation · gated Open weights 6.7 B — ⚠ llama2 211 K 16.3 GB
647 controlnet-union-sdxl-1.0 xinsir · text-to-image Open weights 1.3 B — ✓ apache-2.0 208 K 6.2 GB
648 Qwen3-30B-A3B-GPTQ-Int4 Qwen · text-generation Open weights 30.5 B 41 K ✓ apache-2.0 208 K 23.7 GB
649 MuQ-large-msd-iter OpenMuQ · audio-classification Open weights 330 M — ✗ cc-by-nc-4.0 208 K 2.0 GB
650 DeepSeek-R1-Distill-Llama-70B-GGUF unsloth · text-generation Open weights — 131 K ⚠ llama3.3 208 K 29.5 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.