Local AI Wizard
Moonshot AI / text + image

Kimi K2.6 · thinking

The Kimi K2.6 · thinking checkpoint is published by Moonshot AI for language and reasoning. Its weights are available under Modified MIT; that alone does not establish that its code and all components are open source.

Verified profile

Checkpoint / version
moonshotai/Kimi-K2.6 ↗
Weight license
Modified MIT ↗
Task and modality
language and reasoning · text + image
Count and basis
1000B · manufacturer specification · 32B active
Context
262,144 tokens published for this model
Quality evidence
70.5 · LiveBench 2026-06-25 overall · source ↗
Runtime and precision
No local execution verified. Check the publisher's supported runtime and checkpoint precision; batch and context memory are not measured here.

Local hardware

~758 GB generic Q4 planning memory. Formula: parameters × 0.625 bytes, plus 20% working allowance and 8 GB reserve. This is neither measured VRAM nor checkpoint download size.

Q4 planning estimate only. Check checkpoint format, runtime support, KV cache, context, batch size and offload before choosing hardware.

Explore with context

Memory alone does not prove that a checkpoint runs on a device. Check runtime, quantization, context and batch size in the planner.

Open ranking and planner

Catalog reviewed: 2026-09-24. Benchmark release: 2026-06-25; snapshot collected: 2026-09-22.