Ornith-1.5-397B: hardware requirements
Ornith-1.5-397B needs about 248 GB of memory at Q4_K_M quantization: a 244 GB download plus room for context and a runtime allowance. That is beyond consumer hardware; use it through an API instead.
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?
| Quant | Download | RAM @ 4K | RAM @ 32K | Source |
|---|---|---|---|---|
| Q4_K_Mrecommended | 244 GB | 248 GB | 252 GB | ornith-ai/Ornith-1.5-397B-GGUF |
| Q5_K_M | 286 GB | 290 GB | 294 GB | ornith-ai/Ornith-1.5-397B-GGUF |
| Q6_K | 331 GB | 335 GB | 338 GB | ornith-ai/Ornith-1.5-397B-GGUF |
| Q8_0 | 429 GB | 432 GB | 436 GB | ornith-ai/Ornith-1.5-397B-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).