Ornith-1.5-397B: hardware requirements

Ornith-1.5-397B needs about 248 GB of memory at Q4 quantization — a 244 GB download plus room for context and overhead. That is beyond consumer hardware; use it through an API instead.

Parameters
403B
Tier
Server only
Licence
See model card
Released
2026-08-18

This is a mixture-of-experts model. Only a fraction of its 403B parameters are used for each token, so it runs faster than its size suggests — but all of it still has to fit in memory. The speed is that of a small model; the memory requirement is that of a large one. More on this →

Will it run on your machine?

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_Mrecommended244 GB248 GB252 GBmeasured
Q5_K_M286 GB290 GB294 GBmeasured
Q6_K331 GB335 GB338 GBmeasured
Q8_0429 GB432 GB436 GBmeasured
BF16807 GB811 GB814 GBestimated

“Measured” sizes are read from published GGUF files (ornith-ai/Ornith-1.5-397B-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

Model card on HuggingFace →API specs & pricing →Verified 2026-09-14Tracked for 12 months after release