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 Mac M3 · 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 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
$
648 models
#ModelParamsContextCommercial use30dOn Mac M3 · 24 GB
301 xlm-roberta-base-language-detection papluca · text-classification 280 M 512 ✓ mit 557 K 1.8 GB
302 rtdetr_v2_r18vd PekingU · object-detection 20 M — ✓ apache-2.0 557 K 0.6 GB
303 phi-2 microsoft · text-generation 2.8 B 2 K ✓ mit 556 K 7.0 GB
304 wav2vec2-xls-r-300m-cv7-turkish mpoyraz · ASR 300 M — ✓ cc-by-4.0 556 K 1.2 GB
305 inclusively-classification E-MIMIC · text-classification 110 M 512 ✗ cc-by-nc-sa-4.0 552 K 1.0 GB
306 paraphrase-albert-small-v2 sentence-transformers · sentence-similarity 10 M 512 ✓ apache-2.0 551 K 0.6 GB
307 macbert4csc-base-chinese shibing624 · text-generation 100 M 512 ✓ apache-2.0 543 K 1.0 GB
308 gpt-oss-20b-GGUF unsloth · text-generation — 131 K ✓ apache-2.0 543 K 13.1 GB
309 resnet-50 microsoft · image-classification 30 M — ✓ apache-2.0 542 K 0.6 GB
310 ko-sroberta-multitask jhgan · sentence-similarity 110 M 512 unknown 540 K 1.0 GB
311 gpt-neo-125m EleutherAI · text-generation 150 M 2 K ✓ mit 538 K 1.1 GB
312 whisper-bemba-stt AbelZimba · ASR 240 M — unknown 534 K 1.6 GB
313 Qwen3-Embedding-4B-W4A16-G128 boboliu · feature-extraction 4.1 B 41 K ✓ apache-2.0 532 K 4.0 GB
314 whisper-medium-gguf handy-computer · ASR — — ✓ apache-2.0 529 K 1.1 GB
315 Huihui-DeepSeek-V4-Flash-0731-abliterated-GGUF huihui-ai · text-generation — — ✓ mit 526 K 12.5 GB
316 Qwen3-VL-Embedding-8B-FP8 RamManavalan · feature-extraction 8.8 B — ✓ apache-2.0 525 K 13.5 GB
317 Ornith-1.0-9B-GGUF unsloth · text-generation — — ✓ mit 520 K 5.3 GB
318 distil-large-v3 distil-whisper · ASR 760 M — ✓ mit 517 K 5.6 GB
319 jina-embeddings-v5-text-nano jinaai · feature-extraction 210 M 8 K ✗ cc-by-nc-4.0 515 K 1.1 GB
320 qwen3-4b-base-dapo-v4 ReliquaryForge · text-generation 4.0 B 33 K ✓ apache-2.0 515 K 10.0 GB
321 Qwen2.5-Coder-7B-Instruct-GPTQ-Int4 Qwen · text-generation 7.6 B 33 K ✓ apache-2.0 515 K 7.8 GB
322 open-vakgyata onecxi · audio-classification 60 M — ✗ cc-by-nc-4.0 507 K 0.8 GB
323 bloom-560m bigscience · text-generation 560 M — ⚠ bigscience-bloom-rail-1.0 502 K 1.8 GB
324 wav2vec2-xls-r-300m-sk-cv8 comodoro · ASR 300 M — ✓ apache-2.0 502 K 1.2 GB
325 lambda unslothai · feature-extraction — — unknown 498 K 0.5 GB
326 VibeVoice-1.5B microsoft · text-to-speech 2.7 B — ✓ mit 497 K 6.9 GB
327 snowflake-arctic-embed-s Snowflake · sentence-similarity 30 M 512 ✓ apache-2.0 496 K 0.7 GB
328 pythia-160m-deduped EleutherAI · text-generation 210 M 2 K ✓ apache-2.0 492 K 0.9 GB
329 ruri-v3-310m cl-nagoya · sentence-similarity 310 M 8 K ✓ apache-2.0 492 K 1.9 GB
330 resnet34.a1_in1k timm · image-classification 20 M — ✓ apache-2.0 492 K 0.6 GB
331 sat-3l-sm segment-any-text · token-classification 210 M 514 ✓ mit 491 K 1.5 GB
332 cryptobert ElKulako · text-classification 120 M 512 ✓ mit 483 K 1.1 GB
333 resnet18.a3_in1k timm · image-classification 10 M — ✓ apache-2.0 483 K 0.6 GB
334 gemma-4-12B-coder-fable5-composer2.5-v1-GGUF yuxinlu1 · text-generation — — ✓ apache-2.0 483 K 5.8 GB
335 SmolLM2-360M HuggingFaceTB · text-generation 360 M 8 K ✓ apache-2.0 481 K 1.4 GB
336 snowflake-arctic-embed-l Snowflake · sentence-similarity 334 M 512 ✓ apache-2.0 480 K 2.0 GB
337 Parable-Qwen3-4B-Claude-Fable-5-GGUF AnkitAI · text-generation — — ✓ apache-2.0 479 K 3.2 GB
338 Qwen3-4B-GGUF unsloth · text-generation — 41 K ✓ apache-2.0 474 K 2.3 GB
339 sentence-bert-base-ja-mean-tokens-v2 sonoisa · feature-extraction 110 M 512 cc-by-sa-4.0 474 K 1.0 GB
340 wav2vec2-large-xlsr-japanese-hiragana vumichien · ASR 320 M — ✓ apache-2.0 472 K 1.9 GB
341 wav2vec2-large-xls-r-300m-sinhala-low-LR-part1 SpideyDLK · ASR 320 M — unknown 469 K 1.9 GB
342 wav2vec2-large-xlsr-53-basque stefan-it · ASR 320 M — ✓ apache-2.0 468 K 1.9 GB
343 msmarco-distilbert-base-tas-b sentence-transformers · sentence-similarity 66 M 512 ✓ apache-2.0 463 K 0.8 GB
344 DeepSeek-Coder-V2-Lite-Instruct-GGUF bartowski · text-generation — — other 461 K 7.1 GB
345 pplx-embed-v1-0.6b perplexity-ai · feature-extraction 600 M 33 K ✓ mit 461 K 3.2 GB
346 mimi kyutai · feature-extraction 100 M 8 K ✓ cc-by-4.0 458 K 0.9 GB
347 MedCPT-Query-Encoder ncbi · feature-extraction 110 M 512 other 454 K 1.0 GB
348 vietnamese-bi-encoder bkai-foundation-models · sentence-similarity 130 M 256 ✓ apache-2.0 454 K 1.1 GB
349 indic-conformer-600m-multilingual ai4bharat · ASR · gated 600 M — ✓ mit 453 K 1.9 GB
350 vit_base_patch16_224.augreg2_in21k_ft_in1k timm · image-classification 90 M — ✓ apache-2.0 450 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.