Moonshot AI · open weights · updated July 2026

Kimi K2 Thinking

Parameters
1T / 32B active
Context window
256K tokens
License
Modified MIT
Modalities
text
Released
2025-11-06

Kimi K2 Thinking was Moonshot's November 2025 reasoning release: a trillion-parameter MoE trained for long chains of thought and sustained tool use, reportedly executing 200–300 sequential tool calls without human intervention. At release it beat proprietary frontiers on several agentic benchmarks — a genuine 'open-weight catches up' moment.

It ships INT4-native thanks to quantization-aware training, roughly halving the memory footprint typical of its class. K2.5 has since superseded it as Moonshot's flagship, but K2 Thinking remains the text-only reasoning specialist in the K2 line and a common choice on hosted inference platforms.

K2 Thinking specifications

VendorMoonshot AI (China)
ArchitectureMixture-of-Experts reasoning model, native INT4 (quantization-aware training)
Total parameters1T
Active parameters32B
Context window256K tokens
Modalitiestext
LicenseModified MIT — free commercial use; attribution required above 100M monthly active users or $20M monthly revenue
Release date2025-11-06
WeightsHugging Face · GitHub

Benchmarks and reported results

BenchmarkResultNote
Humanity's Last Exam (with tools)44.9%at release, November 2025
Sequential tool calls without drift200–300vendor-reported agentic stability

Running K2 Thinking locally

Ships INT4-native from quantization-aware training (~594GB), which halves memory versus FP8 trillion-parameter peers. Still multi-GPU server territory — but notably efficient for its class.

What K2 Thinking is best for

  • Long-horizon agentic tasks and heavy tool use
  • Text-only reasoning workloads where K2.5's multimodality is unneeded
  • Memory-efficient serving of a trillion-parameter model (INT4-native)

Frequently asked questions

Should I use Kimi K2 Thinking or Kimi K2.5?

K2.5 is the newer flagship and adds native image/video understanding plus Agent Swarm. K2 Thinking remains a strong text-only reasoning model and its INT4-native weights are cheaper to serve. New projects generally start with K2.5.

What does INT4-native mean for K2 Thinking?

The model was trained with quantization-aware training so the released INT4 weights (~594GB) are the intended serving format, not an afterthought — you get the memory savings without the usual post-hoc quantization quality loss.