DeepSeek-V2
DeepSeek-V2 is a state-of-the-art Mixture-of-Experts (MoE) language model introduced by DeepSeek-AI, characterized by its economical training and efficient inference capabilities. With a total of 236 billion parameters, of which only 21 billion are active per token, it supports a context length of up to 128K tokens. DeepSeek-V2 employs innovative architectures like Multi-head Latent Attention (MLA) for efficient inference by compressing the Key-Value (KV) cache and DeepSeekMoE for cost-effective training through sparse computation. This model significantly outperforms its predecessor, DeepSeek 67B, by saving 42.5% in training costs, reducing the KV cache by 93.3%, and enhancing generation throughput by 5.76 times. Pretrained on an 8.1 trillion token corpus, DeepSeek-V2 excels in language understanding, coding, and reasoning tasks, making it a top-tier performer among open-source models.
Learn more
GLM-4.5
GLM‑4.5 is Z.ai’s latest flagship model in the GLM family, engineered with 355 billion total parameters (32 billion active) and a companion GLM‑4.5‑Air variant (106 billion total, 12 billion active) to unify advanced reasoning, coding, and agentic capabilities in one architecture. It operates in a “thinking” mode for complex, multi‑step reasoning and tool use, and a “non‑thinking” mode for instant responses, supporting up to 128 K token context length and native function calling. Available via the Z.ai chat platform and API, with open weights on HuggingFace and ModelScope, GLM‑4.5 ingests diverse inputs to solve general problem‑solving, common‑sense reasoning, coding from scratch or within existing projects, and end‑to‑end agent workflows such as web browsing and slide generation. Built on a Mixture‑of‑Experts design with loss‑free balance routing, grouped‑query attention, and an MTP layer for speculative decoding, it delivers enterprise‑grade performance.
Learn more
GLM-4.7-Flash
GLM-4.7 Flash is a lightweight variant of GLM-4.7, Z.ai’s flagship large language model designed for advanced coding, reasoning, and multi-step task execution with strong agentic performance and a very large context window. It is an MoE-based model optimized for efficient inference that balances performance and resource use, enabling deployment on local machines with moderate memory requirements while maintaining deep reasoning, coding, and agentic task abilities. GLM-4.7 itself advances over earlier generations with enhanced programming capabilities, stable multi-step reasoning, context preservation across turns, and improved tool-calling workflows, and supports very long context lengths (up to ~200 K tokens) for complex tasks that span large inputs or outputs. The Flash variant retains many of these strengths in a smaller footprint, offering competitive benchmark performance in coding and reasoning tasks for models in its size class.
Learn more
MiMo-V2-Flash
MiMo-V2-Flash is an open weight large language model developed by Xiaomi based on a Mixture-of-Experts (MoE) architecture that blends high performance with inference efficiency. It has 309 billion total parameters but activates only 15 billion active parameters per inference, letting it balance reasoning quality and computational efficiency while supporting extremely long context handling, for tasks like long-document understanding, code generation, and multi-step agent workflows. It incorporates a hybrid attention mechanism that interleaves sliding-window and global attention layers to reduce memory usage and maintain long-range comprehension, and it uses a Multi-Token Prediction (MTP) design that accelerates inference by processing batches of tokens in parallel. MiMo-V2-Flash delivers very fast generation speeds (up to ~150 tokens/second) and is optimized for agentic applications requiring sustained reasoning and multi-turn interactions.
Learn more
