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
551 Llama-3.2-3B meta-llama · text-generation · gated Open weights 3.2 B — ⚠ llama3.2 269 K 8.0 GB
552 Noct-Q-Uncensored-Qwen-Image-2.1 Noctaluna · text-to-image Open weights 7.1 B — other 269 K 17.5 GB
553 SmolLM2-1.7B-Instruct HuggingFaceTB · text-generation Open weights 1.7 B 8 K ✓ apache-2.0 267 K 4.5 GB
554 taardis-27b-full-ternary CodeMasterCody3D · text-generation Open weights 27.0 B — ✓ apache-2.0 267 K 12.4 GB
555 Kimi-K3-DSpark RadixArk · text-generation Open weights 2.3 B 1.0 M unknown 266 K 5.8 GB
556 gliner2.5-multi-v1 fastino · token-classification Open weights 287 M — ✓ apache-2.0 266 K 1.8 GB
557 Qwen3-30B-A3B-GGUF Qwen · text-generation Open weights — — ✓ apache-2.0 265 K 20.9 GB
558 Ornith-1.5-9B-MLX-4bit ornith-ai · text-generation Open weights 9.0 B — unknown 265 K 7.4 GB
559 Qwen2.5-Coder-7B-Instruct-4bit mlx-community · text-generation Open weights 1.2 B 33 K ✓ apache-2.0 264 K 5.4 GB
560 phishing-distilbert-cyber207 ptouch · text-classification Open weights 67 M 512 unknown 264 K 0.8 GB
561 segformer-b0-finetuned-ade-512-512 Xenova · image-segmentation Open weights <0.1 M — unknown 263 K —
562 densenetblur121d.ra_in1k timm · image-classification Open weights 8.1 M — ✓ apache-2.0 262 K 0.5 GB
563 Qwen3.8-27B-NVFP4 nvidia · text-generation Open weights 27.0 B — ✓ apache-2.0 260 K 28.7 GB
564 TwIL-LM3 webAI-Official · text-generation Open weights 3.1 B 66 K other 260 K 3.1 GB
565 Qwen-Image-2.1-Turbo-GGUF AtomicChat · text-to-image Open weights — — other 259 K 3.3 GB
566 waiIllustriousSDXL_v170 LyliaEngine · text-to-image Open weights — — cdla-permissive-2.0 259 K 8.1 GB
567 rubert-tiny-toxicity cointegrated · text-classification Open weights 10 M 512 ✓ mit 258 K 0.6 GB
568 LFM2.5-1.2B-Instruct-GGUF LiquidAI · text-generation Open weights 1.2 B 128 K other 257 K 1.4 GB
569 Kwaipilot_KAT-Coder-V2.5-Dev-GGUF bartowski · text-generation Open weights — — ✓ apache-2.0 257 K 11.3 GB
570 shieldgemma-9b google · text-generation · gated Open weights 9.2 B — ⚠ gemma 256 K 22.2 GB
571 RMBG-1.4 briaai · image-segmentation Open weights 40 M — other 256 K 0.7 GB
572 Qwen-Image-2.1 Qwen · text-to-image Open weights 7.1 B — other 253 K 38.0 GB
573 Llama-3.2-3B-Instruct-GGUF unsloth · text-generation Open weights — 131 K ⚠ llama3.2 253 K 2.0 GB
574 Qwen2.5-1.5B-apeach jason9693 · text-classification Open weights 1.5 B 131 K unknown 251 K 7.5 GB
575 Spark-X2.5-1.7B-GGUF XHToken · text-generation Open weights 1.7 B — ✓ apache-2.0 251 K 2.0 GB
576 Ling-3.0-tiny-GGUF bloomer010 · text-generation Open weights — 131 K ✓ mit 248 K 2.4 GB
577 Z-Image-Turbo-GGUF leejet · text-to-image Open weights — — ✓ apache-2.0 247 K 3.4 GB
578 FLUX.1-dev-gguf city96 · text-to-image Open weights — — other 247 K 4.9 GB
579 xlm-roberta-large-ner-hrl Davlan · token-classification Open weights 560 M 512 ✓ afl-3.0 246 K 3.0 GB
580 DeepSeek-V4-Flash-GGUF bartowski · text-generation Open weights — — ✓ mit 245 K 44.1 GB
581 indictrans2-en-indic-dist-200M ai4bharat · translation · gated Open weights 275 M — ✓ mit 244 K 1.7 GB
582 h2ovl-mississippi-800m h2oai · text-generation Open weights 830 M — ✓ apache-2.0 242 K 2.4 GB
583 cryptobert ElKulako · text-classification Open weights 120 M 512 ✓ mit 241 K 1.1 GB
584 gliner_large-v2 urchade · token-classification Open weights 460 M — ✓ apache-2.0 240 K 2.6 GB
585 Qwen3-8B-FP8 nvidia · text-generation Open weights 8.2 B 41 K ✓ apache-2.0 240 K 12.1 GB
586 Phi-3-mini-128k-instruct microsoft · text-generation Open weights 3.8 B 131 K ✓ mit 239 K 9.5 GB
587 Vikhr-Nemo-12B-Instruct-R-21-09-24 Vikhrmodels · text-generation Open weights 12.3 B 1.0 M ✓ apache-2.0 239 K 30.8 GB
588 s1-mini-GGUF superwhisper · text-generation Open weights — — other 239 K 1.0 GB
589 Qwen2-0.5B-Instruct Qwen · text-generation Open weights 490 M 33 K ✓ apache-2.0 238 K 1.7 GB
590 Llama-3.1-8B-Instruct unsloth · text-generation Open weights 8.0 B 131 K ⚠ llama3.1 238 K 19.4 GB
591 gemma-3-270m google · text-generation · gated Open weights 270 M — ⚠ gemma 238 K 1.1 GB
592 SmolLM-135M-Instruct-FP32 modularai · text-generation Open weights 135 M 2 K unknown 238 K 1.1 GB
593 MiniCPM5-1B openbmb · text-generation Open weights 1.1 B 131 K ✓ apache-2.0 236 K 3.0 GB
594 nsfw-classifier giacomoarienti · image-classification Open weights 90 M — ✗ cc-by-nc-nd-4.0 236 K 0.9 GB
595 POCKET-26B-GGUF FINAL-Bench · text-generation Open weights 26.0 B — ✓ apache-2.0 234 K 16.6 GB
596 rtdetr_r50vd PekingU · object-detection Open weights 40 M — ✓ apache-2.0 234 K 0.7 GB
597 roberta-large-mnli FacebookAI · text-classification Open weights 360 M 512 ✓ mit 234 K 2.1 GB
598 Llama-3.2-3B-Instruct-FP8-dynamic RedHatAI · text-generation Open weights 3.6 B 131 K ⚠ llama3.2 233 K 5.9 GB
599 granite-3.3-2b-instruct ibm-granite · text-generation Open weights 2.5 B 131 K ✓ apache-2.0 233 K 6.5 GB
600 Ornith-1.0-35B-FP8 ornith-ai · text-generation Open weights 35.1 B — ✓ mit 233 K 47.2 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.