LongCat-2.0
1.6T MoE trained entirely on AI ASICs. LongCat-2.0 is an MIT-licensed 1.6T-parameter MoE model with ~48B active parameters, 1M context, LongCat Sparse Attention, and post-training for coding and agentic workflows.
반응 (1)
비슷한 프로덕트
설명이 비슷한 순
Kimi K2
moonshotai.github.ioThe 1T parameter open model for agentic intelligence
GLM-5
z.aiOpen-weights model for long-horizon agentic engineering
Implementation of the LLaMA language model based on nanoGPT. Supports flash attention, Int8 and GPTQ 4bit quantization, LoRA and LLaMA-Adapter fine-tuning, pre-training. Apache 2.0-licensed.
LongShot AI — 2.0
longshot.aiAI platform for all your content needs
DeepSeek-VL2
github.comMoE vision-language, now easier to access