Language
Inkling (MoE, multimodal)
Thinking Machines Inkling — 975B-total multimodal MoE, 41B active, routing each token to 6 of 256 experts plus 2 shared across 66 layers. Hybrid local/global attention, 1M context. Accepts text, images and 16kHz WAV audio via a hierarchical patch encoder and discrete audio tokens, all projected into one hidden space; output is text. Apache-2.0.
Apache 2.0Source verified
Specification
Model ID
inklingFamily
inkling
Modality
Language
Parameters
975B (MoE, 41B active)
Context
1,048,576 tokens
Quantization
UD-Q4_K_XL
Weights
546.7 GB
Minimum RAM
620 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
# Serve it
tenzro model serve inkling
# 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"}]}'Same family