AImodelsComparison.com 1,115 models
Menu
Models Best of Trending Can I run it? Methodology About
Updated 2026-10-15 · ranked by real download data

Models that fit in 12 GB

Ranked nightly from our download snapshots of the Hugging Face catalog. Every entry shows its licence and what hardware it realistically needs.

#ModelParamsContextCommercial use30dMin VRAM
01 all-MiniLM-L6-v2 +1 variant sentence-transformers · sentence-similarity 20 M 512 ✓ apache-2.0 218.1 M from 0.6 GB
02 bge-small-en-v1.5 BAAI · feature-extraction 30 M 512 ✓ mit 59.4 M from 0.7 GB
03 paraphrase-multilingual-MiniLM-L12-v2 sentence-transformers · sentence-similarity 120 M 512 ✓ apache-2.0 47.2 M from 1.0 GB
04 Qwen3-0.6B Qwen · text-generation 750 M 41 K ✓ apache-2.0 30.5 M from 2.3 GB
05 t5-small google-t5 · translation 60 M — ✓ apache-2.0 23.8 M from 0.8 GB
06 mobilenetv3_small_100.lamb_in1k timm · image-classification <0.1 M — ✓ apache-2.0 21.5 M from 0.5 GB
07 all-mpnet-base-v2 sentence-transformers · sentence-similarity 110 M 512 ✓ apache-2.0 18.1 M from 1.0 GB
08 gpt2 openai-community · text-generation 140 M — ✓ mit 16.0 M from 1.1 GB
09 bge-reranker-v2-m3 BAAI · text-classification 570 M 8 K ✓ apache-2.0 15.9 M from 3.1 GB
10 nomic-embed-text-v1.5 nomic-ai · sentence-similarity 140 M 2 K ✓ apache-2.0 13.1 M from 1.1 GB
11 vit-base-patch16-224 google · image-classification 90 M — ✓ apache-2.0 12.8 M from 0.9 GB
12 Qwen3-4B Qwen · text-generation 4.0 B 41 K ✓ apache-2.0 12.6 M from 10.0 GB
13 locate-anything.cpp-gguf mudler · object-detection 3.8 B — other 12.3 M from 6.3 GB
14 Kokoro-82M hexgrad · text-to-speech 82 M — ✓ apache-2.0 10.5 M from 0.7 GB
15 bge-large-en-v1.5 BAAI · feature-extraction 340 M 512 ✓ mit 10.1 M from 2.0 GB
16 multilingual-e5-small intfloat · sentence-similarity 120 M 512 ✓ mit 9.8 M from 1.0 GB
17 paraphrase-multilingual-mpnet-base-v2 sentence-transformers · sentence-similarity 280 M 512 ✓ apache-2.0 9.6 M from 1.8 GB
18 bge-base-en-v1.5 +1 variant BAAI · feature-extraction 110 M 512 ✓ mit 9.2 M from 1.0 GB
19 Qwen3-Embedding-0.6B Qwen · feature-extraction 600 M 33 K ✓ apache-2.0 8.6 M from 1.9 GB
20 Qwen3.5-4B Qwen · image-text-to-text 4.7 B — ✓ apache-2.0 7.9 M from 11.5 GB
21 clap-htsat-fused laion · audio-classification 150 M — ✓ apache-2.0 7.8 M from 1.2 GB
22 multilingual-e5-large intfloat · feature-extraction 560 M 512 ✓ mit 6.8 M from 3.0 GB
23 multilingual-e5-base intfloat · sentence-similarity 280 M 512 ✓ mit 6.7 M from 1.8 GB
24 Llama-3.2-1B-Instruct meta-llama · text-generation 1.2 B — ⚠ llama3.2 6.4 M from 3.4 GB
25 whisper-large-v3-turbo openai · ASR 810 M — ✓ mit 6.3 M from 2.4 GB
Membership and ranking refresh nightly after the snapshot run. VRAM is an estimate for the smallest quantization at 8K context — methodology.