Compatibility check
Can I run Inkling Small on Apple M2 Ultra (76-core GPU)?
Partially — with CPU offload.best quant:
167.7 GB of weights, plus 6.6 GB for the software that runs it and the smallest conversation it can hold, comes to 174.3 GB against the 144 GB this 192 GB device leaves free.
Decode speed
—
Usable context
—
Memory
192 GB
Spills to system RAM
Spills to system RAMest
Too large
Plan B — rent it
Inkling Small is hosted by 2 providers from $1.20 per 1M output tokens (OpenRouter).Compare providers →
