Open-Source Large Language Models (LLMs)
- 01. DeepSeek-V3.2 — Reasoning-first models built for agents. Now available on web, app & API.
- 02. MiMo-V2-Flash. It is a powerful, efficient, and ultra-fast foundation language model that particularly excels in reasoning, coding, and agentic scenarios
- 03. Kimi-K2.5 from Moonshot AI is a trillion-parameter MoE model (32B active parameters) that takes a unique approach: it integrates vision natively from the beginning of pretraining The model was trained on approximately 15 trillion mixed vision and text tokens, with a constant vision-text mixing ratio throughout
- 04. GLM-4.7-Flash - As the strongest model in the 30B class, GLM-4.7-Flash offers a new option for lightweight deployment that balances performance and efficiency.
- 05. GPT-OSS-120b is anopen-weight model, which fits into a single H100 GPU (117B parameters with 5.1B active parameters).
- 06. Qwen3-235B-A22B-Instruct-2507, packs 235B total parameters (22B active per token across 128 experts) and delivers state-of-the-art performance on instruction following, coding, math, and science benchmarks
- 07. Meta's Llama 4 series introduces natively multimodal models (Llama 4 Scout and Llama 4 Maverick ) capable of processing both text and images from the ground up.