baidu/Unlimited-OCR
9h
4.4K
1.2M
- Collected
What it costs to run this
3.3
| Precision | Needs | Cheapest that fits |
|---|---|---|
| 16-bit | 9.3 | Tesla P100 |
| 8-bit | 4.7 | Quadro P2000 |
| 4-bit | 2.3 | Quadro P2000 |
Weights plus attention cache, with 15% added for activations and allocator overhead. Everything here is arithmetic — we do not measure speed, so we do not rank chips by it. See all GPU prices
New image-text-to-text model. Tags: unlimited-ocr, feature-extraction, baidu, vision-language, ocr, custom_code, image-text-to-text, multilingual
overfeed.news indexes and links. We publish a short excerpt — the full article stays at Hugging Face New Models.
More from Hugging Face New Models
Log in to follow this source
tencent/Youtu-Parsing-Omni
New image-text-to-text model. Tags: youtu_vita, text-generation, document-parsing, ocr, omni, multimodal, audio, video
abenzerps/Qwen-Image-2.1-Uncensored-Quantized
New text-to-image model. Tags: gguf, qwen, image-generation, comfyui, comfyui-gguf, mlx, fp8, nvfp4
Mia-AiLab/GLM-5.3-Flash-EXL3-4bpw-TensorFold-Ablit
New image-text-to-text model. Tags: glm5_next, glm, glm-5.3, glm-5.3-flash, exl3, tensorfold, abliterated, uncensored
Cloudflare/clef-omni
New image-text-to-text model. Tags: qwen3_omni_moe, text-to-audio, clef, cloudflare, systemone, decision-model, qwen3-omni, post-train