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 4090 · 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
$
719 models
#ModelParamsContextCommercial use30dOn RTX 4090 · 24 GB
301 RMBG-2.0 briaai · image-segmentation · gated 220 M — other 622 K 1.5 GB
302 MiniCPM-SALA-AWQ-8bit cyankiwi · text-generation 3.1 B 524 K ✓ apache-2.0 616 K 12.7 GB
303 gte-large thenlper · sentence-similarity 340 M 512 ✓ mit 616 K 1.3 GB
304 SmolLM3-3B-Base HuggingFaceTB · text-generation 3.1 B 66 K ✓ apache-2.0 615 K 7.7 GB
305 SmolLM3-3B HuggingFaceTB · text-generation 3.1 B 66 K ✓ apache-2.0 614 K 7.7 GB
306 EXAONE-3.5-7.8B-Instruct-AWQ LGAI-EXAONE · text-generation 7.8 B 33 K other 614 K 7.5 GB
307 MiniCPM5-1B openbmb · text-generation 1.1 B 131 K ✓ apache-2.0 611 K 3.0 GB
308 repvgg_a0.rvgg_in1k timm · image-classification 10 M — ✓ mit 606 K 0.5 GB
309 VieNeu-TTS-v3-Turbo pnnbao-ump · text-to-speech 130 M 1 K ✓ apache-2.0 605 K 1.1 GB
310 Qwen2.5-Coder-3B-Instruct Qwen · text-generation 3.1 B 33 K other 604 K 7.8 GB
311 Qwen2-1.5B-Instruct Qwen · text-generation 1.5 B 33 K ✓ apache-2.0 601 K 4.1 GB
312 bge-small-en-v1.5 michaelfeil · feature-extraction 30 M 512 ✓ mit 599 K 0.7 GB
313 Qwen3-ASR-0.6B Qwen · ASR 940 M — ✓ apache-2.0 598 K 2.7 GB
314 detr-resnet-50 facebook · object-detection 40 M 1 K ✓ apache-2.0 591 K 0.7 GB
315 Qwen3-Reranker-4B-W4A16-G128 boboliu · text-classification 4.1 B 41 K ✓ apache-2.0 586 K 4.0 GB
316 LFM2.5-230M-GGUF LiquidAI · text-generation — — other 586 K 0.7 GB
317 Parable-Qwen3-8B-Claude-Fable-5-GGUF AnkitAI · text-generation — — ✓ apache-2.0 583 K 6.0 GB
318 parakeet-tdt-0.6b-v3 nvidia · ASR 630 M — ✓ cc-by-4.0 577 K 1.4 GB
319 convnext_tiny.in12k_ft_in1k timm · image-classification 30 M — ✓ apache-2.0 577 K 0.6 GB
320 table-transformer-detection microsoft · object-detection 30 M 1 K ✓ mit 576 K 0.6 GB
321 parakeet-tdt-0.6b-v3-gguf handy-computer · ASR — — ✓ cc-by-4.0 575 K 1.0 GB
322 japanese-gpt-neox-small rinna · text-generation 200 M 2 K ✓ mit 575 K 1.3 GB
323 SmolLM-1.7B-Instruct-quantized.w4a16 nm-testing · text-generation 1.8 B 2 K ✓ apache-2.0 571 K 2.7 GB
324 LFM2.5-8B-A1B-GGUF LiquidAI · text-generation — — other 571 K 5.8 GB
325 Qwen2.5-Coder-1.5B-Instruct Qwen · text-generation 1.5 B 33 K ✓ apache-2.0 567 K 4.1 GB
326 wav2vec2-large-xls-r-300m-welsh infinitejoy · ASR 300 M — ✓ apache-2.0 567 K 1.2 GB
327 bge-reranker-v2.5-gemma2-lightweight-gptq boboliu · text-generation 9.2 B 8 K unknown 563 K 8.7 GB
328 e5-small-v2 intfloat · sentence-similarity 30 M 512 ✓ mit 558 K 0.7 GB
329 xlm-roberta-base-language-detection papluca · text-classification 280 M 512 ✓ mit 557 K 1.8 GB
330 rtdetr_v2_r18vd PekingU · object-detection 20 M — ✓ apache-2.0 557 K 0.6 GB
331 phi-2 microsoft · text-generation 2.8 B 2 K ✓ mit 556 K 7.0 GB
332 wav2vec2-xls-r-300m-cv7-turkish mpoyraz · ASR 300 M — ✓ cc-by-4.0 556 K 1.2 GB
333 inclusively-classification E-MIMIC · text-classification 110 M 512 ✗ cc-by-nc-sa-4.0 552 K 1.0 GB
334 paraphrase-albert-small-v2 sentence-transformers · sentence-similarity 10 M 512 ✓ apache-2.0 551 K 0.6 GB
335 Ornith-1.5-9B ornith-ai · text-generation 9.7 B — ✓ mit 546 K 23.2 GB
336 macbert4csc-base-chinese shibing624 · text-generation 100 M 512 ✓ apache-2.0 543 K 1.0 GB
337 gpt-oss-20b-GGUF unsloth · text-generation — 131 K ✓ apache-2.0 543 K 13.1 GB
338 resnet-50 microsoft · image-classification 30 M — ✓ apache-2.0 542 K 0.6 GB
339 ko-sroberta-multitask jhgan · sentence-similarity 110 M 512 unknown 540 K 1.0 GB
340 gpt-neo-125m EleutherAI · text-generation 150 M 2 K ✓ mit 538 K 1.1 GB
341 whisper-bemba-stt AbelZimba · ASR 240 M — unknown 534 K 1.6 GB
342 Llama-3.1-8B meta-llama · text-generation · gated 8.0 B — ⚠ llama3.1 534 K 19.4 GB
343 Qwen3-Embedding-4B-W4A16-G128 boboliu · feature-extraction 4.1 B 41 K ✓ apache-2.0 532 K 4.0 GB
344 whisper-medium-gguf handy-computer · ASR — — ✓ apache-2.0 529 K 1.1 GB
345 Huihui-DeepSeek-V4-Flash-0731-abliterated-GGUF huihui-ai · text-generation — — ✓ mit 526 K 12.5 GB
346 Qwen3-VL-Embedding-8B-FP8 RamManavalan · feature-extraction 8.8 B — ✓ apache-2.0 525 K 13.5 GB
347 Ornith-1.0-9B-GGUF unsloth · text-generation — — ✓ mit 520 K 5.3 GB
348 distil-large-v3 distil-whisper · ASR 760 M — ✓ mit 517 K 5.6 GB
349 jina-embeddings-v5-text-nano jinaai · feature-extraction 210 M 8 K ✗ cc-by-nc-4.0 515 K 1.1 GB
350 qwen3-4b-base-dapo-v4 ReliquaryForge · text-generation 4.0 B 33 K ✓ apache-2.0 515 K 10.0 GB
VRAM figures are estimates for the smallest available quantization at 8K context — see /methodology. Downloads refresh nightly from the Hugging Face API.