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
551 Llama-3.2-3B-Instruct-FP8-dynamic RedHatAI · text-generation 3.6 B 131 K ⚠ llama3.2 277 K 5.9 GB
552 MuQ-large-msd-iter OpenMuQ · audio-classification 330 M — ✗ cc-by-nc-4.0 277 K 2.0 GB
553 vit-age-classifier nateraw · image-classification 90 M — unknown 275 K 0.9 GB
554 Meta-Llama-3-8B meta-llama · text-generation · gated 8.0 B — ⚠ llama3 275 K 19.4 GB
555 MiniCPM5-2B-DSpark openbmb · text-generation 324 M 131 K ✓ apache-2.0 275 K 1.3 GB
556 Qwen3-14B-GGUF MaziyarPanahi · text-generation — — unknown 274 K 6.8 GB
557 gemma-4-31B-it-scotoma-2-GGUF ReadyArt · text-generation — — ✓ apache-2.0 274 K 13.8 GB
558 vit_tiny_r_s16_p8_224.augreg_in21k timm · image-classification 10 M — ✓ apache-2.0 274 K 0.5 GB
559 Qwen3-4B-GGUF MaziyarPanahi · text-generation — — unknown 272 K 2.3 GB
560 tiny_starcoder_py bigcode · text-generation 160 M — bigcode-openrail-m 272 K 1.2 GB
561 Qwen2.5-Coder-7B-Instruct-GGUF Qwen · text-generation — — ✓ apache-2.0 272 K 3.8 GB
562 gpt-oss-20b-MXFP4-Q8 mlx-community · text-generation 20.9 B 131 K ✓ apache-2.0 271 K 16.9 GB
563 DeepSeek-R1-Distill-Qwen-7B deepseek-ai · text-generation 7.6 B 131 K ✓ mit 271 K 18.4 GB
564 DeepSeek-R1-0528-Qwen3-8B-MLX-8bit lmstudio-community · text-generation 2.3 B 131 K ✓ mit 271 K 10.4 GB
565 CodonTransformer adibvafa · token-classification 90 M 4 K ✓ apache-2.0 270 K 0.9 GB
566 Qwen3-1.7B-GGUF MaziyarPanahi · text-generation — — unknown 270 K 1.5 GB
567 Qwen3-0.6B-FP8 Qwen · text-generation 750 M 41 K ✓ apache-2.0 270 K 1.8 GB
568 FLUX.1-dev-gguf city96 · text-to-image — — other 269 K 4.9 GB
569 NVIDIA-Nemotron-3.5-Lightning-30B-A3B-GGUF ggml-org · text-generation — — other 269 K 21.3 GB
570 Qwen3-8B-GGUF MaziyarPanahi · text-generation — — unknown 269 K 4.1 GB
571 Qwen3-4B-AWQ Qwen · text-generation 4.0 B 41 K ✓ apache-2.0 268 K 4.0 GB
572 taardis-27b-full-ternary CodeMasterCody3D · text-generation — — ✓ apache-2.0 268 K 8.4 GB
573 Qwen3-30B-A3B-GGUF MaziyarPanahi · text-generation — — unknown 266 K 12.9 GB
574 Qwen3-32B-GGUF MaziyarPanahi · text-generation — — unknown 266 K 14.1 GB
575 openai-gpt openai-community · text-generation 120 M — ✓ mit 265 K 1.0 GB
576 Qwen3-30B-A3B-GGUF Qwen · text-generation — — ✓ apache-2.0 265 K 20.9 GB
577 llama-3-8b-instruct-awq casperhansen · text-generation 8.0 B 8 K unknown 265 K 8.0 GB
578 Apodex-1.1-mini-GGUF abenzerps · text-generation — — ✓ apache-2.0 264 K 10.2 GB
579 Llama-Guard-3-1B alpindale · text-generation 1.5 B 131 K ⚠ llama3.2 264 K 4.0 GB
580 xlm-roberta-base-ner-hrl Davlan · token-classification 280 M 512 ✓ afl-3.0 262 K 1.8 GB
581 Llama-3.2-1B-Instruct unsloth · text-generation 1.2 B 131 K ⚠ llama3.2 262 K 3.4 GB
582 OpenMed-NER-PharmaDetect-SuperClinical-434M OpenMed · token-classification 430 M 512 ✓ apache-2.0 262 K 1.5 GB
583 nsfw-classifier giacomoarienti · image-classification 90 M — ✗ cc-by-nc-nd-4.0 260 K 0.9 GB
584 Spark-X2.5-4B-GGUF XHToken · text-generation 4.0 B — ✓ apache-2.0 259 K 4.0 GB
585 Qwen2.5-Coder-7B-Instruct-4bit mlx-community · text-generation 1.2 B 33 K ✓ apache-2.0 258 K 5.4 GB
586 Pony_Diffusion_V6_XL LyliaEngine · text-to-image — — cdla-permissive-2.0 258 K 8.5 GB
587 convnextv2-base-22k-384 facebook · image-classification 90 M — ✓ apache-2.0 253 K 0.9 GB
588 bert-small-pii-detection gravitee-io · token-classification 30 M 512 ✓ apache-2.0 252 K 0.6 GB
589 Qwen2.5-1.5B-apeach jason9693 · text-classification 1.5 B 131 K unknown 251 K 7.5 GB
590 Meta-Llama-3.1-8B-Instruct unsloth · text-generation 8.0 B 131 K ⚠ llama3.1 250 K 19.4 GB
591 OpenMed-PII-SuperClinical-Small-44M-v1 OpenMed · token-classification 140 M 512 ✓ apache-2.0 250 K 1.1 GB
592 sarashina2.2-0.5b-instruct-v0.1 sbintuitions · text-generation 790 M 8 K ✓ mit 248 K 2.4 GB
593 Qwen3.8-27B-NVFP4-MTP-GGUF esatapedico · text-generation — — ✓ apache-2.0 248 K 36.9 GB
594 SmolLM2-1.7B-Instruct HuggingFaceTB · text-generation 1.7 B 8 K ✓ apache-2.0 247 K 4.5 GB
595 convnextv2_large.fcmae_ft_in22k_in1k_384 timm · image-classification 200 M — ✗ cc-by-nc-4.0 246 K 1.4 GB
596 xlm-roberta-large-ner-hrl Davlan · token-classification 560 M 512 ✓ afl-3.0 246 K 3.0 GB
597 Qwen3.6-35B-A3B-Claude-4.6-Opus-Reasoning-Distilled-GGUF hesamation · text-generation — — ✓ apache-2.0 245 K 23.8 GB
598 DeepSeek-V4-Flash-GGUF bartowski · text-generation — — ✓ mit 245 K 44.1 GB
599 plant-identity umutbozdag · image-classification 90 M — unknown 245 K 0.9 GB
600 Meta-Llama-3.1-8B-Instruct-AWQ-INT4 hugging-quants · text-generation 8.0 B 131 K ⚠ llama3.1 245 K 8.0 GB
VRAM figures are estimates for the smallest available quantization at 8K context — see /methodology. Downloads refresh nightly from the Hugging Face API.