Loading…
Your privacy choices
Necessary storage keeps the site working. Analytics and advertising stay off unless you allow them. Cookie notice
Some records were last checked a while ago; the values shown are the last published ones.
| Inputs | Weights | Providers | |||
|---|---|---|---|---|---|
| Qwen3-VL-2B-Instruct-1M-GGUFCommunity | 0 | ||||
| Nemotron Nano V2 12Bcortecs | 128,000 tokens Per models.dev; not confirmed by the developer | Text, Image Per models.dev; not confirmed by the developer | Per models.dev; not confirmed by the developer | 1 | |
| Qwen3 Vl 32B Instruct GGUFCommunityAlibaba | 262,144 tokens Per Hugging Face; not confirmed by the developer | Text, Image, Video Per Hugging Face; not confirmed by the developer | 0 | ||
| Qwen3 Vl 2B Thinking GGUFCommunityAlibaba | 262,144 tokens Per Hugging Face; not confirmed by the developer | Text, Image, Video Per Hugging Face; not confirmed by the developer | 0 | ||
| Qwen3 Vl 30B A3b Thinking GGUFCommunityAlibaba | 262,144 tokens Per Hugging Face; not confirmed by the developer | Text, Image, Video Per Hugging Face; not confirmed by the developer | 0 | ||
| Glyph-GGUFCommunity | 0 | ||||
| Qwen3 Vl 8B Thinking GGUFCommunityAlibaba | 262,144 tokens Per Hugging Face; not confirmed by the developer | Text, Image, Video Per Hugging Face; not confirmed by the developer | 0 | ||
| Qwen3 Vl 32B Thinking GGUFCommunityAlibaba | 262,144 tokens Per Hugging Face; not confirmed by the developer | Text, Image, Video Per Hugging Face; not confirmed by the developer | 0 | ||
| Qwen3 Vl 30B A3b Instruct GGUFCommunityAlibaba | Text, Image, Video Per Hugging Face; not confirmed by the developer | 0 | |||
| Chandra-OCR-GGUFCommunity | 0 | ||||
| Qwen3 Vl 235B A22b Thinking GGUFCommunityAlibaba | Text, Image, Video Per Hugging Face; not confirmed by the developer | 0 | |||
| Nova Premier 1.0 | 1,000,000 tokens Per source catalogues; not confirmed by the developer | Text, Image Per source catalogues; not confirmed by the developer | Per source catalogues; not confirmed by the developer | 2 | |
| Qwen3 Vl 2B Instruct GGUFCommunityAlibaba | 262,144 tokens Per Hugging Face; not confirmed by the developer | Text, Image, Video Per Hugging Face; not confirmed by the developer | 0 | ||
| Qwen3 Vl 8B Instruct GGUFCommunityAlibaba | 262,144 tokens Per Hugging Face; not confirmed by the developer | 0 | |||
| Qwen3 Vl 4B Thinking GGUFCommunityAlibaba | 262,144 tokens Per Hugging Face; not confirmed by the developer | Text, Image, Video Per Hugging Face; not confirmed by the developer | 0 | ||
| Qwen3-VL-2B-Thinking-1M-GGUFCommunity | 0 | ||||
| Qwen3 Vl 235B A22b Instruct GGUFCommunityAlibaba | 262,144 tokens Per Hugging Face; not confirmed by the developer | Text, Image, Video Per Hugging Face; not confirmed by the developer | 0 | ||
| JustRL-DeepSeek-1.5B | 131,072 tokens Per Hugging Face; not confirmed by the developer | Text Per Hugging Face; not confirmed by the developer | Per Hugging Face; not confirmed by the developer | 0 | |
| Qwen3-VL-32B-Thinking-MLX-8bitCommunity | Per Hugging Face; not confirmed by the developer | 0 | |||
| Dots.ocr.basedots-studio | 131,072 tokens Per Hugging Face; not confirmed by the developer | 0 | |||
| Qwen3-VL-8B-Instruct-GGUFCommunity | 0 | ||||
| nvidia_Qwen3-Nemotron-32B-RLBFF-GGUFCommunity | Text Per Hugging Face; not confirmed by the developer | 0 | |||
| JanusCoder-8B-GGUFCommunity | 0 | ||||
| Preferred-MedRECT-32Bpfnet | 40,960 tokens Per Hugging Face; not confirmed by the developer | Text Per Hugging Face; not confirmed by the developer | 0 | ||
| Qwen3 Vl 4B Instruct GGUFCommunityAlibaba | 262,144 tokens Per Hugging Face; not confirmed by the developer | Text, Image, Video Per Hugging Face; not confirmed by the developer | 0 |