Weights & Biases

Mellum2-12B-A2.5B-Instruct is a fast MoE model with 131K context built for coding, tool use, and low-latency AI workflows.

MoE model with a highly sparse architecture designed for high-throughput and low latency with strong coding capabilities.

MiniMax M3 is a multimodal MoE model with 23B active parameters optimized for coding and agentic workflows.

An efficient multilingual, dense, instruction-tuned model, optimized by OpenPipe for building agents with finetuning.

Efficient multilingual, Mixture-of-Experts, instruction-tuned model, optimized for logical reasoning.

High-performance Mixture-of-Experts model optimized for structured reasoning, math, and long-form generation.

Qwen3-30B-A3B-Instruct-2507 is a 30.5B MoE instruction-tuned model with enhanced reasoning, coding, and long-context understanding.

Mixture-of-Experts model optimized for agentic coding tasks such as function calling, tool use, and long-context reasoning.

Qwen3.5-27B is a dense model from the Qwen3.5 family built for high performance across a large range of benchmarks.

Qwen3.5-35B-A3B is an open-weights multimodal MoE model built for efficient, high-throughput inference across chat, reasoning, and agentic tasks.

Qwen3.6-27B is a 27B dense multimodal model with 262K context built for flagship-level agentic coding.

Qwen3.6-35B-A3B is an MoE multimodal model with 262K context optimized for agentic coding workflows.

A large hybrid model that supports both thinking and non-thinking modes via prompt templates.

DeepSeek V4-Flash is an MoE model with 1M context length great for coding, reasoning, and agentic workloads.

DeepSeek V4-Pro is a 1.6T-parameter MoE model with 49B active parameters excelling at advanced reasoning, coding, and complex agentic workloads.

Gemma 4 31B Dense is designed for advanced reasoning, agentic workflows, and longer context and is natively trained on 140+ languages.

Granite 4.1 8B is a long-context instruct model capable of enhanced tool calling, instruction following, and chat capabilities.

Efficient conversational model optimized for responsive multilingual chatbot interactions.

Efficient conversational model optimized for responsive multilingual chatbot interactions.

Multilingual model excelling in conversational tasks, detailed instruction-following, and coding.

Compact, efficient model ideal for fast responses in resource-constrained environments.

Kimi K2.5 is a multimodal Mixture-of-Experts language model featuring 32 billion activated parameters and a total of 1 trillion parameters.

Kimi K2.6 is a multimodal Mixture-of-Experts language model featuring 32 billion activated parameters and a total of 1 trillion parameters.

Kimi K2.7 Code is a 1T-parameter MoE model with 32B active parameters purpose-built for long-horizon agentic coding and software engineering.

Nemotron 3 is a LatentMoE model designed to deliver strong agentic, reasoning, and conversational capabilities.

Nemotron 3 Ultra is a powerful MoE model designed for long-running agents across coding, deep research, and enterprise automation.

Efficient Mixture-of-Experts model designed for high-reasoning, agentic and general-purpose use cases.

Lower latency Mixture-of-Experts model trained on OpenAI's Harmony response format with reasoning capabilities.

Powerful MoE model for long-horizon agentic engineering and advanced reasoning.

GLM-5.2 is a Mixture-of-Experts language model featuring 40 billion activated parameters and a total of 744 billion parameters.