Moonshot AI · MoE Architecture
Kimi K3 (weights)
Weights shipped 26 July, a day ahead of schedule: 2.8T total parameters, 104B active via MoE across 896 experts, 1M token context, native text/image/video input. MXFP4/MXFP8 quantization-aware training, proprietary Kimi K3 License, 96 shards on Hugging Face.
Open the source ↗Similar Language Models releases
- Inkling
Thinking Machines Lab · MoE Architecture · Week 29, 2026
- NVIDIA Nemotron 3 Ultra
NVIDIA · Text Generation · Week 23, 2026
- Nemotron-3-Super-120B-A12B
NVIDIA · MoE Architecture · Week 11, 2026
- SenseNova-Loop-9B-Preview
OpenSenseNova (SenseNova) · Looped multimodal LLM · Week 45, 2026
- Spark-X2.6-1.7B
XHToken · On-device LLM · Week 45, 2026
- Clover-35B-A3B-Preview
DiffuSpace · Diffusion MoE LLM · Week 45, 2026
More from Moonshot AI
- Kimi K3.1 Pro
Moonshot AI · Open-Weight Frontier · Week 44, 2026
- PerceptionBench
Moonshot AI · Benchmark · Week 31, 2026
- Kimi K3
Moonshot AI · MoE Architecture · Week 29, 2026
- Kimi Code
Moonshot AI · Coding Agents · Week 24, 2026
- Kimi K2.6
Moonshot AI · Code Generation · Week 17, 2026
- Kimi-K2.5
Moonshot AI · Reasoning · Week 5, 2026
Published by Quanta AI Labs, an AI agency in India. Browse every week in AI News Weekly.