Models

OpenCoder is an open and reproducible code LLM family which includes 1.5B and 8B models, supporting chat in English and Chinese languages.

DeepCoder is a fully open-Source 14B coder model at O3-mini level, with a 1.5B version also available.

Tülu 3 is a leading instruction following model family, offering fully open-source data, code, and recipes by the The Allen Institute for AI.

Merge of the Open Orca OpenChat model and the Garage-bAInd Platypus 2 model. Designed for chat and code generation.

Beam is an open model by Reflection designed to deliver strong performance for areas such as agentic tool use, coding and general reasoning with an emphasis on token efficient usage.

Rnj-1 is a family of 8B parameter open-weight, dense models trained from scratch by Essential AI, optimized for code and STEM with capabilities on par with SOTA open-weight models.

An open-source Mixture-of-Experts code language model that achieves performance comparable to GPT4-Turbo in code-specific tasks.

StarCoder2 is the next generation of transparently trained open code LLMs that comes in three sizes: 3B, 7B and 15B parameters.

Yi-Coder is a series of open-source code language models that delivers state-of-the-art coding performance with fewer than 10 billion parameters.

OpenCoder is an open and reproducible code LLM family for coding which includes 1.5B and 8B models, supporting multiple languages

A small Qwen3 4 billion parameter model trained on nvidia/OpenCodeReasoning for coding tasks.

Based on DeepSeek R1 because OpenCode tries to verify on the registry for tool compatibility

OpenHands LM is built on the foundation of Qwen Coder 2.5 Instruct 32B, leveraging its powerful base capabilities for coding tasks.

OpenHands LM is built on the foundation of Qwen Coder 2.5 Instruct 32B, leveraging its powerful base capabilities for coding tasks.

第二代 OmniCoder，基于 Qwen3.5-9B 微调。仅对助手 token 进行训练（与 v1 不同）：不再出现重复循环，在长时间的智能体会话中能够稳定进行工具调用。 原文链接：https://hf.co/Tesslate/OmniCoder-2-9B

Instinct is Continue's state-of-the-art open Next Edit model. Robustly fine-tuned from Qwen2.5-Coder-7B, Instinct intelligently predicts your next move to keep you in flow.

Qwen2.5-Coder-32B-Instruct fine-tuned on a decontaminated version of the codeforces dataset.

This is an AI model based on the Gemma4 Model Family, but designed to address issues such as sycophancy or unnecessary praise that may arise in AI models. (It has the ability to reason.) This has no connection to the OpenAssistans project.

GCM (Generative Coding Model) is an AI project focused on building a specialized coding model that understands programming, debugging, and software development. The goal is to create a powerful but efficient coding AI that can run on consumer hardware