How much RAM does Inkling-2-Small need?

Inkling-2-Small needs about 398 GB of memory at Published quantization with 4K context. The download itself is 394 GB; the extra covers the context cache and a runtime allowance.

Can I run Inkling-2-Small on a laptop?

Not on typical consumer hardware. Inkling-2-Small needs 398 GB, which is beyond a normal laptop or desktop.

Inkling-2-Small: hardware requirements

Inkling-2-Small needs about 398 GB of memory at Published quantization: a 394 GB download plus room for context and a runtime allowance. That is beyond consumer hardware; use it through an API instead.

Parameters

383B

Tier

Server only

Licence

See model card

Released

2026-07-16

Will it run on your machine?

8GB RAMNot enough memory 16GB RAMNot enough memory 24GB RAMNot enough memory 32GB RAMNot enough memory 64GB RAMNot enough memory 128GB RAMNot enough memory 8GB VRAMNot enough memory 12GB VRAMNot enough memory 16GB VRAMNot enough memory 24GB VRAMNot enough memory 32GB VRAMNot enough memory

Use it without your own hardware

OpenRouter lists Inkling 2 Small at $0.30 per million input tokens and $1.00 per million output tokens. Artificial Analysis measured hosted providers generating 85 tokens per second (Nov 13, 2026).

Price as listed on OpenRouter today. Speed is for hosted servers, not a home computer.

Download sizes by quantization

Lower quantization means a smaller file and less memory, at some cost to quality. Q4_K_M is the usual starting point. What is this?

Quant	Download	RAM @ 4K	RAM @ 32K	Source
Published	394 GB	398 GB	403 GB	thinkingmachines/Inkling-2-Small

Download sizes are measured from the published files named in the Source column. The RAM columns add the context cache, calculated from the model's configuration, and a runtime allowance of 10% of the download (at least 0.5GB, at most 3GB).

Model card on HuggingFace →API specs & pricing →Verified 2026-11-13Listed for 120 days after release