Kimi K2 Thinking

moonshotai · released 2025-11-06 · other license

Kimi K2 Thinking is Moonshot's 1T-parameter (32B active) open-weight reasoning agent (Nov 2025), leading open models on agentic and reasoning benchmarks. Artificial Analysis rates it #1 among comparable open models (index 41).

Key specs

TypeLocal open-weight
Parameters1058.12B total · MoE, — active
Architecturekimi_k2
Context window262K tokens
Knowledge cutoff
Modalitiestext
Recommended backends
Minimum viable rig

Benchmark scores

GPQA Diamond84.5%
SWE-bench Verified71.3%
AIME94.5%
MMLU-Pro84.6%
BFCL v3 (tool use)
Composite score7.4
Community ratingNo reviews yet

VRAM & disk per quantization

QuantVRAMDiskRAMContext
Q4_K_M615.2 GB613.7 GB262K

Strengths & weaknesses

Strengths: SOTA open-weight agentic reasoning with stable long-horizon tool use; Strong HLE-with-tools and agentic search; Native INT4, 256K context

Weaknesses: Verbose / high token use; Text-only, no image input