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
651 Bielik-11B-v3.0-Instruct-awq speakleash · text-generation Open weights 11.3 B 33 K ✓ apache-2.0 208 K 9.0 GB
652 Qwen3.6-35B-A3B-DFlash z-lab · text-generation Open weights 390 M 262 K ✓ apache-2.0 208 K 1.4 GB
653 Mistral-7B-Instruct-v0.3-AWQ solidrust · text-generation Open weights 7.3 B 33 K ✓ apache-2.0 208 K 6.2 GB
654 The_GuageLLM_23M Hai929 · text-generation Open weights 20 M — ✓ apache-2.0 207 K 0.6 GB
655 Bonsai-27B-gguf prism-ml · text-generation Open weights — — ✓ apache-2.0 207 K 1.2 GB
656 Qwen3Guard-Gen-4B Qwen · text-generation Open weights 4.4 B 33 K ✓ apache-2.0 207 K 10.9 GB
657 Qwen2.5-Coder-1.5B-Instruct-GGUF Qwen · text-generation Open weights 1.5 B 33 K ✓ apache-2.0 206 K 1.6 GB
658 gemma-3-1b-it google · text-generation · gated Open weights 1.0 B — ⚠ gemma 206 K 2.8 GB
659 Mistral-7B-Instruct-v0.2-AWQ TheBloke · text-generation Open weights 7.2 B 33 K ✓ apache-2.0 205 K 6.2 GB
660 Nemotron-Labs-Diffusion-8B nvidia · text-generation Open weights 8.5 B 262 K other 204 K 20.6 GB
661 granite-guardian-3.3-8b ibm-granite · text-generation Open weights 8.2 B 131 K ✓ apache-2.0 204 K 19.7 GB
662 DeepSeek-V2-Lite-Chat deepseek-ai · text-generation Open weights 15.7 B 164 K other 204 K 37.4 GB
663 Qwen2.5-3B Qwen · text-generation Open weights 3.1 B 33 K other 203 K 7.8 GB
664 medgemma-27b-text-it-GPTQ bbarn4 · text-generation Open weights 4.8 B 131 K other 202 K 18.8 GB
665 LFM2.5-1.2B-Instruct LiquidAI · text-generation Open weights 1.2 B 128 K other 201 K 3.3 GB
666 Yi-Coder-9B-Chat-GGUF MaziyarPanahi · text-generation Open weights — — unknown 201 K 2.7 GB
667 OLMoE-1B-7B-0125-Instruct allenai · text-generation Open weights 6.9 B 4 K ✓ apache-2.0 201 K 16.8 GB
668 gemma-7b google · text-generation · gated Open weights 8.5 B — ⚠ gemma 200 K 20.6 GB
669 Qwen_Qwen3-Next-80B-A3B-Thinking-GGUF bartowski · text-generation Open weights — — ✓ apache-2.0 200 K 18.7 GB
670 Qwen3.5-35B-A3B-APEX-GGUF mudler · text-generation Open weights — — ✓ apache-2.0 200 K 28.4 GB
671 glm-4-9b-chat-IMat-GGUF legraphista · text-generation Open weights — — other 200 K 3.9 GB
672 VLM2Vec-Full TIGER-Lab · text-generation Open weights 4.2 B 131 K ✓ apache-2.0 199 K 10.2 GB
673 Qwen2.5-7B-Instruct-1M Qwen · text-generation Open weights 7.6 B 1.0 M ✓ apache-2.0 197 K 18.4 GB
674 Olmo-3-7B-Think allenai · text-generation Open weights 7.3 B 66 K ✓ apache-2.0 197 K 17.7 GB
675 gemma-4-12b-heretic-abliterated-GGUF culturerevolt · text-generation Open weights — — ✓ apache-2.0 196 K 0.7 GB
676 Olmo-3-7B-Instruct allenai · text-generation Open weights 7.3 B 66 K ✓ apache-2.0 196 K 17.7 GB
677 Laguna-S-2.1-GGUF unsloth · text-generation Open weights — — openmdw-1.1 196 K 37.6 GB
678 Qwen2.5-Coder-32B-Instruct-GGUF Qwen · text-generation Open weights — — ✓ apache-2.0 196 K 9.1 GB
679 Qwen3.6-27B-Text-NVFP4-MTP sakamakismile · text-generation Open weights 16.7 B — ✓ apache-2.0 196 K 24.6 GB
680 llama-3-8b-instruct-awq casperhansen · text-generation Open weights 8.0 B 8 K unknown 196 K 8.0 GB
681 Fanar-1-9B-Instruct QCRI · text-generation Open weights 8.8 B 4 K ✓ apache-2.0 195 K 21.1 GB
682 Qwen2.5-3B-Instruct-unsloth-bnb-4bit unsloth · text-generation Open weights 3.2 B 33 K ✓ apache-2.0 195 K 3.6 GB
683 Qwen3-1.7B-GGUF unsloth · text-generation Open weights 1.7 B 41 K ✓ apache-2.0 195 K 1.6 GB
684 Huihui-Qwen3.6-27B-abliterated-NVFP4-MTP sakamakismile · text-generation Open weights 27.0 B — ✓ apache-2.0 195 K 27.2 GB
685 gpt-oss-120b-Eagle3-short-context nvidia · text-generation Open weights 787 M 131 K other 195 K 2.8 GB
686 Qwen2.5-1.5B-Instruct-AWQ Qwen · text-generation Open weights 1.8 B 33 K ✓ apache-2.0 195 K 2.5 GB
687 Llama-Guard-3-8B meta-llama · text-generation · gated Open weights 8.0 B — ⚠ llama3.1 195 K 19.4 GB
688 NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4-DSpark nvidia · text-generation Open weights 760 M 1.0 M other 195 K 2.1 GB
689 TinyLlama-1.1B-Chat-v0.3-GPTQ TheBloke · text-generation Open weights 1.1 B 2 K ✓ apache-2.0 195 K 1.5 GB
690 Illustrious-xl-early-release-v0 OnomaAIResearch · text-to-image Open weights 2.6 B — other 194 K 23.8 GB
691 Qwen3.6-35B-A3B-Claude-4.6-Opus-Reasoning-Distilled-GGUF hesamation · text-generation Open weights — — ✓ apache-2.0 194 K 23.8 GB
692 EuroLLM-1.7B-Instruct utter-project · text-generation Open weights 1.7 B 4 K ✓ apache-2.0 194 K 4.4 GB
693 supergemma4-26b-uncensored-gguf-v2 Jiunsong · text-generation Open weights — — ⚠ gemma 194 K 19.0 GB
694 gemma-2-2b google · text-generation · gated Open weights 2.6 B — ⚠ gemma 193 K 12.4 GB
695 Ornith-1.5-35B-A3B-MLX-8bit ornith-ai · text-generation Open weights 34.7 B — unknown 192 K 46.2 GB
696 Qwen2.5-Coder-14B-Instruct-GGUF Qwen · text-generation Open weights 14.0 B 33 K ✓ apache-2.0 192 K 8.9 GB
697 Llama-3.2-3B-Instruct-GGUF bartowski · text-generation Open weights — — ⚠ llama3.2 191 K 2.3 GB
698 Z-Image-Turbo-FP8 unsloth · text-to-image Open weights 6.2 B — ✓ apache-2.0 190 K 27.9 GB
699 Qwen3.8-27B-DSpark RadixArk · text-generation Open weights 1.9 B 262 K other 190 K 4.9 GB
700 NVIDIA-Nemotron-Nano-9B-v2-FP8 nvidia · text-generation Open weights 8.9 B 131 K other 190 K 13.1 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.