Back to Kimi K2.6 in the gallery

Moonshot AI

Native-multimodal K2.5 successor that keeps the same 1T sparse MoE backbone while targeting stronger long-horizon coding, design, and agent orchestration.

Kimi K2.6 architecture diagram
Kimi K2.6 architecture diagram. Select the diagram to view it at full size.

Architecture and specifications

Scale
1T total, 32B active (3.2% active)
Context (tokens)
262,144
License
Modified MIT License
Date
2026-04-20
Decoder type
Sparse MoE
Attention
MLA
Layer mix
61 MLA
KV cache / token (bf16) info
68.6 KiB · Low
Key detail
Uses the same text architecture as Kimi K2.5, with the main change coming from the multimodal and agentic training recipe.

Training and benchmarks

Pretraining data
Not disclosed The version-specific model card and release post do not give a pretraining-token total. Model card · Release post
Post-training methods
Not disclosed The checked release sources describe capabilities without disclosing a version-specific post-training recipe. Model card · Release post
AA Intelligence Index v4.3.2 info
Total score 27.0 General 38.6 Scientific 22.7 Coding 26.0 Agents 19.1

Further reading and tools