AImodelsComparison.com 1,058 models
Menu
Models Best of Trending Can I run it? Methodology About
1,000 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 88 image-text-to-text 80 sentence-similarity 55 feature-extraction 45 translation 43 text-classification 39 image-classification 32 token-classification 21 text-to-speech 12 audio-classification 10 object-detection 10 image-segmentation 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
$
585 models
#ModelParamsContextCommercial use30dOn RTX 4070 · 16 GB
401 gpt2-medium openai-community · text-generation 380 M — ✓ mit 317 K 2.2 GB
402 xflux_text_encoders XLabs-AI · text-generation 4.8 B — ✓ apache-2.0 317 K 11.7 GB
403 table-transformer-structure-recognition-v1.1-all microsoft · object-detection 30 M — ✓ mit 314 K 0.6 GB
404 The_GuageLLM_23M Hai929 · text-generation 20 M — ✓ apache-2.0 314 K 0.6 GB
405 rubert-tiny-toxicity cointegrated · text-classification 10 M 512 ✓ mit 313 K 0.6 GB
406 phishing-email-detection-distilbert_v2.4.1 cybersectony · text-classification 70 M 512 ✓ apache-2.0 309 K 0.8 GB
407 opt-350m facebook · text-generation 350 M 2 K other 308 K 1.3 GB
408 llmlingua-2-bert-base-multilingual-cased-meetingbank microsoft · token-classification 180 M 512 ✓ apache-2.0 307 K 1.3 GB
409 gpt-j-6b EleutherAI · text-generation 6.0 B — ✓ apache-2.0 304 K 14.6 GB
410 SmolLM2-360M-Instruct HuggingFaceTB · text-generation 360 M 8 K ✓ apache-2.0 303 K 1.4 GB
411 Qwen2-0.5B-Instruct Qwen · text-generation 490 M 33 K ✓ apache-2.0 302 K 1.7 GB
412 prokbert-mini-promoter neuralbioinfo · text-classification 20 M 1 K ✗ cc-by-nc-4.0 302 K 0.6 GB
413 Qwen2.5-14B-bnb-4bit unsloth · text-generation 15.2 B 131 K ✓ apache-2.0 298 K 13.7 GB
414 Qwen3.5-4B-Claude-4.6-Opus-Reasoning-Distilled-GGUF Jackrong · text-generation — — ✓ apache-2.0 297 K 2.5 GB
415 Qwopus-GLM-18B-Merged-GGUF KyleHessling1 · text-generation — — ✓ apache-2.0 295 K 9.2 GB
416 Qwen3-0.6B-GGUF MaziyarPanahi · text-generation — — unknown 295 K 0.9 GB
417 mask2former-swin-large-ade-semantic facebook · image-segmentation 220 M — other 295 K 1.5 GB
418 DeepSeek-R1-0528-Qwen3-8B-MLX-4bit lmstudio-community · text-generation 1.3 B 131 K ✓ mit 293 K 5.8 GB
419 nllb-200-distilled-1.3B facebook · translation 1.3 B 1 K ✗ cc-by-nc-4.0 292 K 3.6 GB
420 voice-gender-classifier JaesungHuh · audio-classification 20 M — ✓ mit 291 K 0.6 GB
421 KoELECTRA-small-v3-modu-ner Leo97 · token-classification 10 M 512 unknown 288 K 0.6 GB
422 Qwen2.5-3B-Instruct-GGUF Qwen · text-generation — — other 286 K 2.0 GB
423 Qwen3.8-Flash-Next-GGUF AtomicChat · text-generation — — other 285 K 1.5 GB
424 Jan-v3.5-4B-gguf janhq · text-generation — — ✓ apache-2.0 284 K 2.8 GB
425 Llama-3.2-1B-Instruct-FP8-dynamic RedHatAI · text-generation 1.5 B 131 K ⚠ llama3.2 283 K 3.0 GB
426 Ornith-1.5-9B-MLX-4bit ornith-ai · text-generation 9.0 B — unknown 283 K 7.4 GB
427 mamba-130m-hf state-spaces · text-generation 130 M — unknown 281 K 1.1 GB
428 Flux2-Klein-9B-True-V2 wikeeyang · text-to-image — — other 281 K 6.8 GB
429 vit_base_patch8_224.augreg2_in21k_ft_in1k timm · image-classification 90 M — ✓ apache-2.0 281 K 0.9 GB
430 Llama-3.2-3B-Instruct-FP8-dynamic RedHatAI · text-generation 3.6 B 131 K ⚠ llama3.2 277 K 5.9 GB
431 MuQ-large-msd-iter OpenMuQ · audio-classification 330 M — ✗ cc-by-nc-4.0 277 K 2.0 GB
432 vit-age-classifier nateraw · image-classification 90 M — unknown 275 K 0.9 GB
433 MiniCPM5-2B-DSpark openbmb · text-generation 324 M 131 K ✓ apache-2.0 275 K 1.3 GB
434 Qwen3-14B-GGUF MaziyarPanahi · text-generation — — unknown 274 K 6.8 GB
435 gemma-4-31B-it-scotoma-2-GGUF ReadyArt · text-generation — — ✓ apache-2.0 274 K 13.8 GB
436 vit_tiny_r_s16_p8_224.augreg_in21k timm · image-classification 10 M — ✓ apache-2.0 274 K 0.5 GB
437 Qwen3-4B-GGUF MaziyarPanahi · text-generation — — unknown 272 K 2.3 GB
438 tiny_starcoder_py bigcode · text-generation 160 M — bigcode-openrail-m 272 K 1.2 GB
439 Qwen2.5-Coder-7B-Instruct-GGUF Qwen · text-generation — — ✓ apache-2.0 272 K 3.8 GB
440 DeepSeek-R1-0528-Qwen3-8B-MLX-8bit lmstudio-community · text-generation 2.3 B 131 K ✓ mit 271 K 10.4 GB
441 CodonTransformer adibvafa · token-classification 90 M 4 K ✓ apache-2.0 270 K 0.9 GB
442 Qwen3-1.7B-GGUF MaziyarPanahi · text-generation — — unknown 270 K 1.5 GB
443 Qwen3-0.6B-FP8 Qwen · text-generation 750 M 41 K ✓ apache-2.0 270 K 1.8 GB
444 FLUX.1-dev-gguf city96 · text-to-image — — other 269 K 4.9 GB
445 Qwen3-8B-GGUF MaziyarPanahi · text-generation — — unknown 269 K 4.1 GB
446 Qwen3-4B-AWQ Qwen · text-generation 4.0 B 41 K ✓ apache-2.0 268 K 4.0 GB
447 taardis-27b-full-ternary CodeMasterCody3D · text-generation — — ✓ apache-2.0 268 K 8.4 GB
448 Qwen3-30B-A3B-GGUF MaziyarPanahi · text-generation — — unknown 266 K 12.9 GB
449 Qwen3-32B-GGUF MaziyarPanahi · text-generation — — unknown 266 K 14.1 GB
450 openai-gpt openai-community · text-generation 120 M — ✓ mit 265 K 1.0 GB
VRAM figures are estimates for the smallest available quantization at 8K context — see /methodology. Downloads refresh nightly from the Hugging Face API.