AImodelsComparison.com 1,058 models
Menu
Models Best of Trending Can I run it? Methodology About
1,058 models · refreshed nightly

Models that run on RTX 3060 · 12 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 413 text-to-image 152 ASR 92 image-text-to-text 89 sentence-similarity 60 feature-extraction 48 translation 48 text-classification 42 image-classification 33 token-classification 29 text-to-speech 12 audio-classification 11 object-detection 11 image-segmentation 10 summarization 8
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
$
573 models
#ModelParamsContextCommercial use30dOn RTX 3060 · 12 GB
351 gemma-3-270m google · text-generation · gated 270 M — ⚠ gemma 395 K 1.1 GB
352 granite-4.1-3b ibm-granite · text-generation 3.4 B 131 K ✓ apache-2.0 393 K 8.5 GB
353 Ternary-Bonsai-8B-gguf prism-ml · text-generation — — ✓ apache-2.0 392 K 2.9 GB
354 Qwen3.8-27B-DFlash2 incoai · text-generation 1.9 B 262 K ✓ apache-2.0 391 K 5.0 GB
355 Kwaipilot_KAT-Coder-V2.5-Dev-GGUF bartowski · text-generation — — ✓ apache-2.0 390 K 11.3 GB
356 Phi-4-mini-instruct microsoft · text-generation 3.8 B 131 K ✓ mit 384 K 9.5 GB
357 TwIL-LM3 webAI-Official · text-generation 3.1 B 66 K other 384 K 3.1 GB
358 rtdetr_r50vd_coco_o365 PekingU · object-detection 40 M — ✓ apache-2.0 380 K 0.7 GB
359 pythia-14m EleutherAI · text-generation 10 M 2 K ✓ apache-2.0 378 K 0.5 GB
360 mistral-7b-v0.3-bnb-4bit unsloth · text-generation 7.5 B 33 K ✓ apache-2.0 377 K 6.2 GB
361 Ornith-1.5-9B-OBLITERATED OBLITERATUS · text-generation 9.7 B — ✓ mit 371 K 6.3 GB
362 segformer-b0-finetuned-ade-512-512 nvidia · image-segmentation <0.1 M — other 368 K 0.5 GB
363 Llama-3.2-3B meta-llama · text-generation · gated 3.2 B — ⚠ llama3.2 368 K 8.0 GB
364 Parable-Granite-4.1-3B-Claude-Fable-5-GGUF AnkitAI · text-generation — — ✓ apache-2.0 366 K 2.8 GB
365 privacy-filter-multilingual-GGUF LocalAI-io · token-classification — — ✓ apache-2.0 366 K 2.3 GB
366 Qwen3.8-27B-DFlash2 z-lab · text-generation 1.9 B 262 K ✓ apache-2.0 364 K 5.0 GB
367 Parable-Granite-4.1-8B-Claude-Fable-5-GGUF AnkitAI · text-generation — — ✓ apache-2.0 362 K 6.1 GB
368 Qwen2.5-Coder-1.5B Qwen · text-generation 1.5 B 33 K ✓ apache-2.0 361 K 4.1 GB
369 MiniCPM5-1B-Claude-Opus-Fable5-V2-Thinking-GGUF GnLOLot · text-generation — — ✓ apache-2.0 360 K 1.8 GB
370 Z-Image-Turbo-GGUF unsloth · text-to-image — — ✓ apache-2.0 356 K 4.5 GB
371 vlt5-base-keywords Voicelab · text-generation 280 M — ✓ cc-by-4.0 355 K 1.8 GB
372 t5-large google-t5 · translation 740 M — ✓ apache-2.0 352 K 3.9 GB
373 amd.Instella-MoE-16B-A3B-Think-GGUF DevQuasar · text-generation — — unknown 351 K 7.7 GB
374 RMBG-1.4 briaai · image-segmentation 40 M — other 349 K 0.7 GB
375 wide_resnet50_2.racm_in1k timm · image-classification 70 M — ✓ apache-2.0 348 K 0.8 GB
376 Agents-A1-4B InternScience · text-generation 4.5 B — ✓ apache-2.0 344 K 11.2 GB
377 Phi-3.5-mini-instruct microsoft · text-generation 3.8 B 131 K ✓ mit 341 K 9.5 GB
378 Qwen2.5-3B Qwen · text-generation 3.1 B 33 K other 338 K 7.8 GB
379 nsfw_image_detector Freepik · image-classification 90 M — ✓ mit 334 K 0.7 GB
380 distilroberta-finetuned-financial-news-sentiment-analysis mrm8488 · text-classification 80 M 512 ✓ apache-2.0 330 K 0.9 GB
381 Qwen3.8-27B-DSpark RadixArk · text-generation 1.9 B 262 K other 329 K 4.9 GB
382 LFM2.5-1.2B-Instruct-GGUF LiquidAI · text-generation — — other 325 K 1.3 GB
383 MiniCPM5-1B-Claude-Opus-Fable5-Thinking-GGUF GnLOLot · text-generation — — ✓ apache-2.0 325 K 1.3 GB
384 deid_roberta_i2b2 obi · token-classification 350 M 512 ✓ mit 324 K 2.1 GB
385 Meta-Llama-3.1-8B-Instruct-GGUF bartowski · text-generation — — ⚠ llama3.1 320 K 3.7 GB
386 Qwen2.5-Math-1.5B-Instruct Qwen · text-generation 1.5 B 4 K ✓ apache-2.0 318 K 4.1 GB
387 gpt2-medium openai-community · text-generation 380 M — ✓ mit 317 K 2.2 GB
388 xflux_text_encoders XLabs-AI · text-generation 4.8 B — ✓ apache-2.0 317 K 11.7 GB
389 table-transformer-structure-recognition-v1.1-all microsoft · object-detection 30 M — ✓ mit 314 K 0.6 GB
390 The_GuageLLM_23M Hai929 · text-generation 20 M — ✓ apache-2.0 314 K 0.6 GB
391 rubert-tiny-toxicity cointegrated · text-classification 10 M 512 ✓ mit 313 K 0.6 GB
392 phishing-email-detection-distilbert_v2.4.1 cybersectony · text-classification 70 M 512 ✓ apache-2.0 309 K 0.8 GB
393 opt-350m facebook · text-generation 350 M 2 K other 308 K 1.3 GB
394 llmlingua-2-bert-base-multilingual-cased-meetingbank microsoft · token-classification 180 M 512 ✓ apache-2.0 307 K 1.3 GB
395 SmolLM2-360M-Instruct HuggingFaceTB · text-generation 360 M 8 K ✓ apache-2.0 303 K 1.4 GB
396 Qwen2-0.5B-Instruct Qwen · text-generation 490 M 33 K ✓ apache-2.0 302 K 1.7 GB
397 prokbert-mini-promoter neuralbioinfo · text-classification 20 M 1 K ✗ cc-by-nc-4.0 302 K 0.6 GB
398 Qwen3.5-4B-Claude-4.6-Opus-Reasoning-Distilled-GGUF Jackrong · text-generation — — ✓ apache-2.0 297 K 2.5 GB
399 Qwopus-GLM-18B-Merged-GGUF KyleHessling1 · text-generation — — ✓ apache-2.0 295 K 9.2 GB
400 Qwen3-0.6B-GGUF MaziyarPanahi · text-generation — — unknown 295 K 0.9 GB
VRAM figures are estimates for the smallest available quantization at 8K context — see /methodology. Downloads refresh nightly from the Hugging Face API.