AImodelsComparison.com 1,011 models
Menu
Models Best of Trending Can I run it? Methodology About
1,011 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 400 text-to-image 150 ASR 89 image-text-to-text 82 sentence-similarity 55 feature-extraction 47 translation 44 text-classification 39 image-classification 32 token-classification 22 text-to-speech 16 audio-classification 12 image-segmentation 8 object-detection 8 summarization 7
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
$
542 models
#ModelParamsContextCommercial use30dOn RTX 4070 · 16 GB
251 nsfw_image_detector Freepik · image-classification 90 M — ✓ mit 591 K 0.7 GB
252 LFM2.5-1.2B-Instruct LiquidAI · text-generation 1.2 B 128 K other 584 K 3.3 GB
253 snowflake-arctic-embed-s Snowflake · sentence-similarity 30 M 512 ✓ apache-2.0 584 K 0.7 GB
254 nb-wav2vec2-1b-bokmaal-v2 NbAiLab · ASR 960 M — ✓ apache-2.0 581 K 4.9 GB
255 Qwen3-Reranker-4B-W4A16-G128 boboliu · text-classification 4.1 B 41 K ✓ apache-2.0 578 K 4.0 GB
256 encodec_24khz facebook · feature-extraction 20 M — unknown 577 K 0.6 GB
257 gemma-2-2b-it google · text-generation · gated 2.6 B — ⚠ gemma 576 K 6.6 GB
258 sentence-bert-base-ja-mean-tokens-v2 sonoisa · feature-extraction 110 M 512 cc-by-sa-4.0 575 K 1.0 GB
259 Qwen3-TTS-12Hz-1.7B-VoiceDesign Qwen · text-to-speech 1.9 B — ✓ apache-2.0 574 K 5.8 GB
260 Phi-4-multimodal-instruct microsoft · ASR 5.6 B 131 K ✓ mit 572 K 15.4 GB
261 gpt2-medium openai-community · text-generation 380 M — ✓ mit 572 K 2.2 GB
262 wav2vec2-xls-r-parlaspeech-hr classla · ASR 320 M — unknown 564 K 1.9 GB
263 gpt-oss-20b-GGUF unsloth · text-generation — 131 K ✓ apache-2.0 560 K 13.1 GB
264 sat-3l-sm segment-any-text · token-classification 210 M 514 ✓ mit 558 K 1.5 GB
265 msmarco-bert-base-dot-v5 sentence-transformers · sentence-similarity 110 M 512 unknown 557 K 1.0 GB
266 Llama-3.2-3B meta-llama · text-generation · gated 3.2 B — ⚠ llama3.2 552 K 8.0 GB
267 whisper-bemba-stt AbelZimba · ASR 240 M — unknown 546 K 1.6 GB
268 Phi-3-mini-4k-instruct microsoft · text-generation 3.8 B 4 K ✓ mit 544 K 9.5 GB
269 detr-resnet-50 facebook · object-detection 40 M 1 K ✓ apache-2.0 544 K 0.7 GB
270 macbert4csc-base-chinese shibing624 · text-generation 100 M 512 ✓ apache-2.0 542 K 1.0 GB
271 gte-base thenlper · sentence-similarity 110 M 512 ✓ mit 541 K 0.8 GB
272 privacy-filter openai · token-classification 1.4 B 131 K ✓ apache-2.0 536 K 6.9 GB
273 Qwen2.5-Coder-7B-Instruct-GPTQ-Int4 Qwen · text-generation 7.6 B 33 K ✓ apache-2.0 536 K 7.8 GB
274 Qwen-AgentWorld-35B-A3B-GGUF unsloth · text-generation — — ✓ apache-2.0 534 K 13.1 GB
275 Qwen3-Embedding-4B-W4A16-G128 boboliu · feature-extraction 4.1 B 41 K ✓ apache-2.0 532 K 4.0 GB
276 jina-clip-v2 jinaai · feature-extraction 870 M — ✗ cc-by-nc-4.0 530 K 2.5 GB
277 granite-speech-3.3-2b ibm-granite · ASR 3.0 B — ✓ apache-2.0 529 K 13.9 GB
278 Qwen2.5-Coder-7B-Instruct-AWQ Qwen · text-generation 7.6 B 33 K ✓ apache-2.0 522 K 7.8 GB
279 inclusively-classification E-MIMIC · text-classification 110 M 512 ✗ cc-by-nc-sa-4.0 521 K 1.0 GB
280 whisper-medium-gguf handy-computer · ASR — — ✓ apache-2.0 518 K 1.1 GB
281 jina-embeddings-v5-text-nano jinaai · feature-extraction 210 M 8 K ✗ cc-by-nc-4.0 515 K 1.1 GB
282 wav2vec2-xls-r-300m-ftspeech saattrupdan · ASR 320 M — other 512 K 1.9 GB
283 fullstop-punctuation-multilang-large oliverguhr · token-classification 560 M 512 ✓ mit 511 K 3.0 GB
284 vit_base_patch16_224.augreg2_in21k_ft_in1k timm · image-classification 90 M — ✓ apache-2.0 510 K 0.9 GB
285 wide_resnet50_2.racm_in1k timm · image-classification 70 M — ✓ apache-2.0 506 K 0.8 GB
286 gemma-2-9b-it-AWQ-INT4 hugging-quants · text-generation 9.2 B 8 K ⚠ gemma 504 K 8.7 GB
287 lambda unslothai · feature-extraction — — unknown 504 K 0.5 GB
288 t5gemma-s-s-prefixlm google · text-generation · gated 310 M — ⚠ gemma 499 K 1.2 GB
289 resnet34.a1_in1k timm · image-classification 20 M — ✓ apache-2.0 495 K 0.6 GB
290 bert-base-turkish-cased-mean-nli-stsb-tr emrecan · sentence-similarity 110 M 512 ✓ apache-2.0 495 K 1.0 GB
291 convnext_tiny.in12k_ft_in1k timm · image-classification 30 M — ✓ apache-2.0 494 K 0.6 GB
292 SmolLM2-360M-Instruct HuggingFaceTB · text-generation 360 M 8 K ✓ apache-2.0 494 K 1.4 GB
293 llmlingua-2-bert-base-multilingual-cased-meetingbank microsoft · token-classification 180 M 512 ✓ apache-2.0 493 K 1.3 GB
294 vietnamese-bi-encoder bkai-foundation-models · sentence-similarity 130 M 256 ✓ apache-2.0 492 K 1.1 GB
295 tiny-mixtral TitanML · text-generation 250 M 131 K unknown 490 K 1.6 GB
296 Meta-Llama-3.1-8B-Instruct-FP8 RedHatAI · text-generation 8.0 B 131 K ⚠ llama3.1 479 K 11.7 GB
297 wav2vec2-large-xlsr-mvc-swahili eddiegulay · ASR 320 M — ✓ apache-2.0 476 K 1.9 GB
298 bge-m3-spa-law-qa littlejohn-ai · sentence-similarity · gated 570 M — ✓ apache-2.0 473 K 3.1 GB
299 typhoon2.5-qwen3-4b typhoon-ai · text-generation 4.0 B 262 K ✓ apache-2.0 468 K 10.0 GB
300 Qwen3-4B-AWQ Qwen · text-generation 4.0 B 41 K ✓ apache-2.0 463 K 4.0 GB
VRAM figures are estimates for the smallest available quantization at 8K context — see /methodology. Downloads refresh nightly from the Hugging Face API.