MedAIBase

MedGemma1.5

MedGemma 1.5 4B is an updated version of the MedGemma 1 4B model, delivers improved accuracy on medical text reasoning and modest improvement on standard 2D image interpretation compared to MedGemma 1 4B. The 4b-it-q4_0 has overfitting! Avoid it.

4b

1,152 Pulls 5 Tags Updated 2 weeks ago

PaddleOCR-VL

PaddleOCR-VL is a SOTA and resource-efficient model tailored for document parsing. Its core component is PaddleOCR-VL-0.9B, a compact yet powerful vision-language model (VLM) .

0.9b

1,016 Pulls 2 Tags Updated 2 weeks ago

Qwen3-VL-Embedding

The Qwen3-VL-Embedding model series are the latest additions to the Qwen family, built upon the recently open-sourced and powerful Qwen3-VL foundation model.

2b

407 Pulls 3 Tags Updated 2 weeks ago

Qwen3-VL-Reranker

The Qwen3-VL-Reranker model series are the latest additions to the Qwen family, built upon the recently open-sourced and powerful Qwen3-VL foundation model.

2b

386 Pulls 3 Tags Updated 2 weeks ago

Tencent-HY-MT1.5

Hunyuan Translation Model Version 1.5 includes a 1.8B translation model, HY-MT1.5-1.8B, and a 7B translation model, HY-MT1.5-7B. Both models focus on supporting mutual translation across 33 languages and incorporating 5 ethnic and dialect variations.

1.8b 7b

302 Pulls 5 Tags Updated 2 weeks ago

TranslateGemma

TranslateGemma is a family of lightweight, state-of-the-art open translation models from Google, based on the Gemma 3 family of models. TranslateGemma models are designed to handle translation tasks across 55 languages.

vision 4b 12b 27b

185 Pulls 12 Tags Updated 1 week ago

MedGemma1.0

MedGemma is a collection of Gemma 3 variants that are trained for performance on medical text and image comprehension.

4b 27b

138 Pulls 6 Tags Updated 2 weeks ago

AntAngelMed

AntAngelMed是由浙江省卫生健康信息中心、蚂蚁健康、浙江省安诊儿医学人工智能科技有限公司共同联合开发的，迄今为止最大且最强大的开源医疗语言模型。

100b

64 Pulls 2 Tags Updated 2 weeks ago

DASD-Thinking

DASD-4B-Thinking is a compact yet capable 4B dense language model specialized in long chain-of-thought (Long-CoT) reasoning across mathematics, code generation, and scientific reasoning. This version has overfitting! Avoid it.

4b

40 Pulls 3 Tags Updated 6 days ago

GLM-4.6V-Flash

GLM-4.6V-Flash (9B) is a lightweight model optimized for local deployment and low-latency applications. It scales its context window to 128k tokens in training and achieves SoTA performance in visual understanding among models of similar parameter scales.

9b

37 Pulls 3 Tags Updated 6 days ago

Ling-flash-2.0

Ling-flash-2.0, a language model with 100B total parameters and 6.1B activated parameters (4.8B non-embedding).

100b

37 Pulls 2 Tags Updated 2 weeks ago

Tencent-Youtu-LLM

Tencent-Youtu-LLM is a new, small, yet powerful LLM, contains only 1.96B parameters, supports 128k long context, and has native agentic talents.

2b

32 Pulls 3 Tags Updated 6 days ago

Ring-flash-2.0

Ring-flash-2.0 has a total of 100B parameters, with only 6.1B activated per inference.

100b

25 Pulls 2 Tags Updated 2 weeks ago

Step3-VL

STEP3-VL-10B is a lightweight open-source foundation model designed to redefine the trade-off between compact efficiency and frontier-level multimodal intelligence. It excels in visual perception, complex reasoning, and human-centric alignment.