Language

Kimi K2.6 (Hybrid Thinking, MoE)

Moonshot AI Kimi K2.6 hybrid-thinking MoE — 1T total params, 256K context. Replica-routed on B200-class infrastructure; Unsloth measures >40 t/s on B200. Recommended `UD-Q2_K_XL` (350GB) for size/quality balance.

MITSource verified

Specification

Model ID

kimi-k2.6

Family

kimi

Modality

Language

Parameters

1T (MoE, 32B active)

Context

262,144 tokens

Quantization

UD-Q4_K_XL

Weights

558.8 GB

Minimum RAM

400 GB

Source

Weights and provenance.

Repository

unsloth/Kimi-K2.6-GGUF

Registry license

MIT

Access

Open — weights fetch without accepting additional terms.

The licence above is the registry's. The source repository either states nothing, states the catch-all “other”, or carries a licence link and base model that its own tag contradicts — a re-quantisation inherits the terms of the weights it derives from. The registry's licence is the one to rely on.

Serve it

# Pull the weights onto a node
tenzro model download kimi-k2.6

# Serve it
tenzro model serve kimi-k2.6

# Or query the registry entry over JSON-RPC
curl https://rpc.tenzro.xyz \
  -X POST -H "Content-Type: application/json" \
  -d '{"jsonrpc":"2.0","id":1,
       "method":"tenzro_getModel",
       "params":[{"model_id":"kimi-k2.6"}]}'

Same family

Kimi K2 Instruct (MoE)

1T (MoE, 32B active, code-focused)

← All models