Language
Inkling Small (MoE, multimodal)
Thinking Machines Inkling Small — 276B-total multimodal MoE, 12B active, 1M context. Accepts text, images and 16kHz WAV audio; output is text. Apache-2.0.
Apache 2.0Source verified
Specification
Model ID
inkling-smallFamily
inkling
Modality
Language
Parameters
276B (MoE, 12B active)
Context
1,048,576 tokens
Quantization
UD-Q4_K_XL
Weights
158.3 GB
Minimum RAM
180 GB
Source
Weights and provenance.
Repository
Registry license
Apache 2.0
Source license
apache-2.0
Access
Open — weights fetch without accepting additional terms.
Serve it
# Pull the weights onto a node
tenzro model download inkling-small
# Serve it
tenzro model serve inkling-small
# 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":"inkling-small"}]}'Same family