# Long context support

Qwen3-Embedding-4B is a text embedding model built on the Qwen3 series, designed specifically for text embedding and ranking tasks, and performs excellently in multilingual text processing and code retrieval.

MedGemma-4B-IT is a medical multimodal model based on Gemma 3, supporting the understanding of medical text and images, and suitable for the development of medical AI applications.

MedGemma is a medical multimodal model developed based on Gemma 3, focusing on medical text and image understanding and supporting the construction of healthcare AI applications.

MedGemma is a medical-specific model series optimized based on Gemma 3, offering a 27-billion-parameter pure-text version specifically optimized for medical text understanding and reasoning.

Qwen2-96M is a miniature language model based on the Qwen2 architecture, containing 96 million parameters and supporting a context length of 8192 tokens, suitable for English text generation tasks.

A 1.5B parameter instruction fine-tuned model designed for Gensyn RL Swarm, supporting local fine-tuning via peer-to-peer reinforcement learning

ZYH-LLM-Qwen2.5-14B-V4 is a large language model improved based on Qwen2.5-14B. It enhances computational accuracy and reasoning ability through multi-stage model merging and distillation techniques.

Japanese BERT model trained by Algomatic team, supporting fill-mask tasks with a context length of up to 8192.

Ganga-2-1b is an instruction fine-tuned model trained on a Hindi dataset and is part of Project Unity, aiming to handle the diversity and richness of Indian languages.

Llama3.1-Typhoon2-8B is a large Thai language model (instructional type) based on the Transformer architecture, capable of handling various language tasks and providing users with efficient and accurate language interaction services.

A state-of-the-art bilingual language model based on the Llama architecture, specially optimized for Korean understanding and generation while maintaining strong English capabilities.

IBM Granite 8B code instruction model, supporting a context length of 128k, focusing on code generation and instruction understanding tasks.

This is a reranking model based on BAAI/bge-reranker-v2-m3 and further fine-tuned on a large-scale Polish text pair dataset, supporting long-context processing.

The Jais series is a bilingual large language model specialized in Arabic language processing, with strong English capabilities and 1.3 billion parameters.

A chat model fine-tuned by H2O.ai with 4 billion parameters, supporting text generation tasks and capable of offline operation on mobile phones.

A large Norwegian language model fine-tuned on instructions based on NorwAI-Mixtral-8x7B, optimized using approximately 9000 high-quality Norwegian instructions.

Gemma is an advanced open-source model trained on high-quality datasets, supporting different context length requirements.

Phi-3 Small is a 7B-parameter lightweight cutting-edge open-source model, optimized for NVIDIA GPUs in ONNX format, supporting 8K context length with strong inference capabilities.

The GGUF quantized version of DeepSeek-V2-Chat, suitable for local deployment and operation.

An 1.8B parameter chat model fine-tuned by H2O.ai, based on adapted Llama 2 architecture with 8192 context length support

A Russian sentence encoder model based on the RoPEBert architecture, supporting a context length of 2048 tokens and excelling in the encodechka benchmark tests.

PhoGPT is an open-source series of 4-billion-parameter Vietnamese language generation models, including the base pre-trained model PhoGPT-4B and its conversational variant PhoGPT-4B-Chat.

PhoGPT is currently the most advanced 4-billion-parameter Vietnamese language generation model series, including the base pre-trained monolingual model PhoGPT-4B and its conversational variant PhoGPT-4B-Chat.

speechless-coder-ds-6.7b is a large language model fine-tuned based on deepseek-ai/deepseek-coder-6.7b, focusing on improving code generation and programming assistance capabilities.

GEITje-7B is a large open-source Dutch language model based on Mistral 7B, significantly enhancing Dutch language capabilities and local knowledge through additional training on 10 billion Dutch text tokens.

Large open-source Dutch conversational model based on Mistral 7B, significantly improving Dutch language capabilities through additional training on 10 billion Dutch text tokens

The first open commercial-use German base language model built on Llama-2, focusing on German language processing

GPT-J 6B fine-tuned model for Python code generation, specialized in Python programming assistance