TPSTokens Per Second

Ornith-1.5-9B: hardware requirements

Ornith-1.5-9B needs about 6.9 GB of memory at Q4 quantization — a 5.8 GB download plus room for context and overhead. That fits a machine with 16GB RAM.

Parameters
9.7B
Tier
Runs on a laptop
Licence
See model card
Released
2026-08-18

Will it run on your machine?

8GB RAMNot enough memory16GB RAMRuns well24GB RAMRuns well32GB RAMRuns well64GB RAMRuns well128GB RAMRuns well8GB VRAMTight fit12GB VRAMRuns well16GB VRAMRuns well24GB VRAMRuns well32GB VRAMRuns well

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?

QuantDownloadRAM @ 4KRAM @ 32KSource
Q4_K_Mrecommended5.8 GB6.9 GB11 GBmeasured
Q5_K_M6.6 GB7.8 GB12 GBmeasured
Q6_K7.6 GB8.9 GB13 GBmeasured
Q8_09.8 GB11 GB15 GBmeasured
BF1619 GB22 GB26 GBmeasured

“Measured” sizes are read from published GGUF files (ornith-ai/Ornith-1.5-9B-GGUF). “Estimated” sizes are derived from the parameter count and are typically within a few percent. The RAM columns add the context cache and runtime overhead to the download size.

Other sizes of Ornith-1.5

Ornith-1.5-35B-A3B36B · 24 GBOrnith-1.5-397B403B · 248 GB
Model card on HuggingFace →API specs & pricing →Verified 2026-09-14Tracked for 12 months after release