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 Mac M3 · 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
$
680 models
#ModelParamsContextCommercial use30dOn Mac M3 · 24 GB
351 sqlcoder-7b-2 defog · text-generation Open weights 6.7 B 16 K cc-by-sa-4.0 441 K 6.8 GB
352 nllb-200-distilled-1.3B facebook · translation Open weights 1.3 B 1 K ✗ cc-by-nc-4.0 440 K 3.6 GB
353 Qwen2.5-0.5B-Instruct-GGUF Qwen · text-generation Open weights — — ✓ apache-2.0 440 K 1.0 GB
354 Apodex-1.1-mini-GGUF abenzerps · text-generation Open weights — — ✓ apache-2.0 439 K 10.2 GB
355 S-PubMedBert-MedQuAD TimKond · sentence-similarity Open weights 110 M 512 ✓ mit 439 K 1.0 GB
356 Qwen3.8-27B-DFlash2 incoai · text-generation Open weights 1.9 B 262 K ✓ apache-2.0 438 K 5.0 GB
357 clipseg-rd64-refined CIDAS · image-segmentation Open weights 150 M — ✓ apache-2.0 437 K 1.2 GB
358 Qwen-Image-2.1-Lightning lightx2v · text-to-image Open weights 7.1 B — unknown 436 K 1.6 GB
359 segformer_b2_clothes mattmdjaga · image-segmentation Open weights 30 M — other 434 K 0.6 GB
360 vram-16 unslothai · feature-extraction Open weights — — unknown 432 K 0.5 GB
361 LFM2.5-24B-A2B-GGUF unsloth · text-generation Open weights 24.0 B 131 K other 430 K 12.3 GB
362 lambda unslothai · feature-extraction Open weights — — unknown 428 K 0.5 GB
363 efficient-splade-VI-BT-large-doc naver · feature-extraction Open weights — 512 ✗ cc-by-nc-sa-4.0 427 K 0.5 GB
364 Qwen3-14B-GGUF Qwen · text-generation Open weights — — ✓ apache-2.0 424 K 10.4 GB
365 maple-preview-GGUF deepgrove · text-generation Open weights — — ✓ mit 424 K 6.5 GB
366 Ling-3.0-tiny-MLX-4bit rapid-mlx · text-generation Open weights 7.9 B 131 K ✓ mit 420 K 6.6 GB
367 Qwen-Image-2512-GGUF unsloth · text-to-image Open weights 20.4 B — ✓ apache-2.0 420 K 12.1 GB
368 german-sentiment-bert oliverguhr · text-classification Open weights 109 M 512 ✓ mit 419 K 1.0 GB
369 Ornith-1.0-9B-GGUF unsloth · text-generation Open weights — — ✓ mit 418 K 5.3 GB
370 llama2-embedding-1b-8k mesolitica · feature-extraction Open weights 947 M 33 K unknown 416 K 4.8 GB
371 pythia-6.9b EleutherAI · text-generation Open weights 7.0 B 2 K ✓ apache-2.0 414 K 16.8 GB
372 RMBG-2.0 briaai · image-segmentation · gated Open weights 221 M — other 408 K 1.5 GB
373 Mistral-7B-v0.1 mistralai · text-generation Open weights 7.2 B 33 K ✓ apache-2.0 405 K 17.5 GB
374 locate-anything.cpp-gguf mudler · object-detection Open weights 3.8 B — other 405 K 6.3 GB
375 vit_base_patch16_224.augreg2_in21k_ft_in1k timm · image-classification Open weights 90 M — ✓ apache-2.0 402 K 0.9 GB
376 Qwen2.5-Coder-1.5B-Instruct Qwen · text-generation Open weights 1.5 B 33 K ✓ apache-2.0 402 K 4.1 GB
377 BioLORD-2023 FremyCompany · sentence-similarity Open weights 110 M 512 other 399 K 1.0 GB
378 LLM2Vec-Meta-Llama-3-8B-Instruct-mntp McGill-NLP · sentence-similarity Open weights 8.0 B 8 K ✓ mit 396 K 1.9 GB
379 mistral-7b-v0.3-bnb-4bit unsloth · text-generation Open weights 7.5 B 33 K ✓ apache-2.0 392 K 6.2 GB
380 Qwen2.5-Coder-1.5B Qwen · text-generation Open weights 1.5 B 33 K ✓ apache-2.0 387 K 4.1 GB
381 SmolLM3-3B HuggingFaceTB · text-generation Open weights 3.1 B 66 K ✓ apache-2.0 386 K 7.7 GB
382 humanizer jialinyyzz · text-generation Open weights 12.0 B — ✓ apache-2.0 380 K 6.6 GB
383 Qwen-Image-2.1-Turbo-GGUF DogukanUrker · text-to-image Open weights — — other 379 K 3.1 GB
384 bloom-560m bigscience · text-generation Open weights 560 M — ⚠ bigscience-bloom-rail-1.0 378 K 1.8 GB
385 Huihui-DeepSeek-V4-Flash-0731-abliterated-GGUF huihui-ai · text-generation Open weights — — ✓ mit 377 K 12.5 GB
386 Qwen2.5-Coder-7B-Instruct-GGUF Qwen · text-generation Open weights — — ✓ apache-2.0 376 K 3.8 GB
387 audiobox-aesthetics facebook · audio-classification Open weights 100 M — ✓ cc-by-4.0 375 K 1.0 GB
388 deid_roberta_i2b2 obi · token-classification Open weights 350 M 512 ✓ mit 369 K 2.1 GB
389 Phi-3.5-mini-instruct microsoft · text-generation Open weights 3.8 B 131 K ✓ mit 367 K 9.5 GB
390 spark-s1-4b-v6-GGUF abhishek085 · text-classification Open weights 4.0 B — ✓ apache-2.0 367 K 4.9 GB
391 Qwen3-4B-Thinking-2507 Qwen · text-generation Open weights 4.0 B 262 K ✓ apache-2.0 364 K 10.0 GB
392 fullstop-punctuation-multilang-large oliverguhr · token-classification Open weights 560 M 512 ✓ mit 363 K 3.0 GB
393 gpt-oss-20b-GGUF ggml-org · text-generation Open weights 20.0 B 131 K ✓ apache-2.0 356 K 4.5 GB
394 roberta-base-openai-detector openai-community · text-classification Open weights 125 M 512 ✓ mit 353 K 1.1 GB
395 convnext_base.fb_in22k_ft_in1k timm · image-classification Open weights 90 M — ✓ apache-2.0 350 K 0.9 GB
396 wide_resnet101_2.tv_in1k timm · image-classification Open weights 127 M — ✓ bsd-3-clause 350 K 1.1 GB
397 Meta-Llama-3.1-8B-Instruct-GGUF bartowski · text-generation Open weights — — ⚠ llama3.1 344 K 3.7 GB
398 Spark-X2.5-4B-GGUF abenzerps · text-generation Open weights 4.0 B — ✓ apache-2.0 338 K 3.7 GB
399 mask2former-swin-large-ade-semantic facebook · image-segmentation Open weights 220 M — other 336 K 1.5 GB
400 Pony_Diffusion_V6_XL LyliaEngine · text-to-image Open weights — — cdla-permissive-2.0 335 K 8.5 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.