Language
Kimi K2.7 Code (MoE)
Moonshot AI Kimi K2.7 Code — code-focused refresh of the K2 series. 1T total / 32B active; 256K context; recent updates target tool-call accuracy on long-horizon coding tasks.
MITSource verified
Specification
Model ID
kimi-k2.7-codeFamily
kimi
Modality
Language
Parameters
1T (MoE, 32B active, code-focused)
Context
262,144 tokens
Quantization
UD-Q4_K_XL
Weights
540.2 GB
Minimum RAM
384 GB
Source
Weights and provenance.
Repository
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-k2.7-code
# Serve it
tenzro model serve kimi-k2.7-code
# 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-k2.7-code"}]}'Same family