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 4070 · 16 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
$
621 models
#ModelParamsContextCommercial use30dOn RTX 4070 · 16 GB
301 gpt-oss-20b-GGUF unsloth · text-generation — 131 K ✓ apache-2.0 543 K 13.1 GB
302 resnet-50 microsoft · image-classification 30 M — ✓ apache-2.0 542 K 0.6 GB
303 ko-sroberta-multitask jhgan · sentence-similarity 110 M 512 unknown 540 K 1.0 GB
304 gpt-neo-125m EleutherAI · text-generation 150 M 2 K ✓ mit 538 K 1.1 GB
305 whisper-bemba-stt AbelZimba · ASR 240 M — unknown 534 K 1.6 GB
306 Qwen3-Embedding-4B-W4A16-G128 boboliu · feature-extraction 4.1 B 41 K ✓ apache-2.0 532 K 4.0 GB
307 whisper-medium-gguf handy-computer · ASR — — ✓ apache-2.0 529 K 1.1 GB
308 Huihui-DeepSeek-V4-Flash-0731-abliterated-GGUF huihui-ai · text-generation — — ✓ mit 526 K 12.5 GB
309 Qwen3-VL-Embedding-8B-FP8 RamManavalan · feature-extraction 8.8 B — ✓ apache-2.0 525 K 13.5 GB
310 Ornith-1.0-9B-GGUF unsloth · text-generation — — ✓ mit 520 K 5.3 GB
311 distil-large-v3 distil-whisper · ASR 760 M — ✓ mit 517 K 5.6 GB
312 jina-embeddings-v5-text-nano jinaai · feature-extraction 210 M 8 K ✗ cc-by-nc-4.0 515 K 1.1 GB
313 qwen3-4b-base-dapo-v4 ReliquaryForge · text-generation 4.0 B 33 K ✓ apache-2.0 515 K 10.0 GB
314 Qwen2.5-Coder-7B-Instruct-GPTQ-Int4 Qwen · text-generation 7.6 B 33 K ✓ apache-2.0 515 K 7.8 GB
315 open-vakgyata onecxi · audio-classification 60 M — ✗ cc-by-nc-4.0 507 K 0.8 GB
316 bloom-560m bigscience · text-generation 560 M — ⚠ bigscience-bloom-rail-1.0 502 K 1.8 GB
317 wav2vec2-xls-r-300m-sk-cv8 comodoro · ASR 300 M — ✓ apache-2.0 502 K 1.2 GB
318 lambda unslothai · feature-extraction — — unknown 498 K 0.5 GB
319 VibeVoice-1.5B microsoft · text-to-speech 2.7 B — ✓ mit 497 K 6.9 GB
320 snowflake-arctic-embed-s Snowflake · sentence-similarity 30 M 512 ✓ apache-2.0 496 K 0.7 GB
321 pythia-160m-deduped EleutherAI · text-generation 210 M 2 K ✓ apache-2.0 492 K 0.9 GB
322 ruri-v3-310m cl-nagoya · sentence-similarity 310 M 8 K ✓ apache-2.0 492 K 1.9 GB
323 resnet34.a1_in1k timm · image-classification 20 M — ✓ apache-2.0 492 K 0.6 GB
324 sat-3l-sm segment-any-text · token-classification 210 M 514 ✓ mit 491 K 1.5 GB
325 cryptobert ElKulako · text-classification 120 M 512 ✓ mit 483 K 1.1 GB
326 resnet18.a3_in1k timm · image-classification 10 M — ✓ apache-2.0 483 K 0.6 GB
327 gemma-4-12B-coder-fable5-composer2.5-v1-GGUF yuxinlu1 · text-generation — — ✓ apache-2.0 483 K 5.8 GB
328 SmolLM2-360M HuggingFaceTB · text-generation 360 M 8 K ✓ apache-2.0 481 K 1.4 GB
329 snowflake-arctic-embed-l Snowflake · sentence-similarity 334 M 512 ✓ apache-2.0 480 K 2.0 GB
330 Parable-Qwen3-4B-Claude-Fable-5-GGUF AnkitAI · text-generation — — ✓ apache-2.0 479 K 3.2 GB
331 Qwen3-4B-GGUF unsloth · text-generation — 41 K ✓ apache-2.0 474 K 2.3 GB
332 sentence-bert-base-ja-mean-tokens-v2 sonoisa · feature-extraction 110 M 512 cc-by-sa-4.0 474 K 1.0 GB
333 wav2vec2-large-xlsr-japanese-hiragana vumichien · ASR 320 M — ✓ apache-2.0 472 K 1.9 GB
334 wav2vec2-large-xls-r-300m-sinhala-low-LR-part1 SpideyDLK · ASR 320 M — unknown 469 K 1.9 GB
335 wav2vec2-large-xlsr-53-basque stefan-it · ASR 320 M — ✓ apache-2.0 468 K 1.9 GB
336 msmarco-distilbert-base-tas-b sentence-transformers · sentence-similarity 66 M 512 ✓ apache-2.0 463 K 0.8 GB
337 DeepSeek-Coder-V2-Lite-Instruct-GGUF bartowski · text-generation — — other 461 K 7.1 GB
338 pplx-embed-v1-0.6b perplexity-ai · feature-extraction 600 M 33 K ✓ mit 461 K 3.2 GB
339 mimi kyutai · feature-extraction 100 M 8 K ✓ cc-by-4.0 458 K 0.9 GB
340 MedCPT-Query-Encoder ncbi · feature-extraction 110 M 512 other 454 K 1.0 GB
341 vietnamese-bi-encoder bkai-foundation-models · sentence-similarity 130 M 256 ✓ apache-2.0 454 K 1.1 GB
342 indic-conformer-600m-multilingual ai4bharat · ASR · gated 600 M — ✓ mit 453 K 1.9 GB
343 vit_base_patch16_224.augreg2_in21k_ft_in1k timm · image-classification 90 M — ✓ apache-2.0 450 K 0.9 GB
344 mask2former-swin-large-cityscapes-semantic facebook · image-segmentation 220 M — other 444 K 1.5 GB
345 zeta-2.1-autoround-W4A16 LeaderboardModel1 · text-generation 2.2 B 33 K unknown 444 K 7.6 GB
346 msmarco-bert-base-dot-v5 sentence-transformers · sentence-similarity 110 M 512 unknown 444 K 1.0 GB
347 Voxtral-Mini-4B-Realtime-2602-gguf handy-computer · ASR — — ✓ apache-2.0 442 K 3.6 GB
348 Bonsai-27B-gguf prism-ml · text-generation — — ✓ apache-2.0 440 K 1.2 GB
349 BioLORD-2023 FremyCompany · sentence-similarity 110 M 512 other 437 K 1.0 GB
350 bge-small-en-v1.5 Xenova · feature-extraction 30 M 512 unknown 433 K 0.6 GB
VRAM figures are estimates for the smallest available quantization at 8K context — see /methodology. Downloads refresh nightly from the Hugging Face API.