Inkling: hardware requirements
Inkling needs about 861 GB of memory at Q8_0 quantization: a 857 GB download plus room for context and a runtime allowance. That is beyond consumer hardware; use it through an API instead.
Will it run on your machine?
Use it without your own hardware
OpenRouter lists Inkling at $1.00 per million input tokens and $4.05 per million output tokens. Artificial Analysis measured hosted providers generating 177 tokens per second (Oct 29, 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 |
|---|---|---|---|---|
| Q8_0 | 857 GB | 861 GB | 869 GB | unsloth/inkling-GGUF |
| BF16 | 1894 GB | 1899 GB | 1907 GB | unsloth/inkling-GGUF |
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).