North-Mini-Code-1.0-fp8: hardware requirements
North-Mini-Code-1.0-fp8 needs about 36 GB of memory at Q4 quantization — a 32 GB download plus room for context and overhead. That fits a machine with 64GB RAM.
This is a mixture-of-experts model. Only a fraction of its 31B 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 |
|---|---|---|---|---|
| Published | 32 GB | 36 GB | 39 GB | measured |
“Measured” sizes are read from published GGUF files (CohereLabs/North-Mini-Code-1.0-fp8). “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.