Language

Kimi K2 Instruct (MoE)

Moonshot AI Kimi K2 MoE — 1T total, 32B active, 128K context

MITSource verified

Specification

Model ID

kimi-k2-instruct

Family

kimi

Modality

Language

Parameters

1T (MoE, 32B active)

Context

131,072 tokens

Quantization

Q4_K_M

Weights

18.8 GB

Minimum RAM

24 GB

Source

Weights and provenance.

Repository

unsloth/Kimi-K2-Instruct-GGUF

Registry license

MIT

Source license

other

Access

Open — weights fetch without accepting additional terms.

The registry records this model as MIT while the source repository states other. Both are shown here rather than one being preferred. Treat the stricter of the two as binding until the discrepancy is resolved upstream.

Serve it

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

# Serve it
tenzro model serve kimi-k2-instruct

# 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-instruct"}]}'

Same family

Kimi K2.5 (MoE)

1T (MoE, 32B active)

Kimi K2.6 (Hybrid Thinking, MoE)

1T (MoE, 32B active)

Kimi K2.7 Code (MoE)

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

← All models