K2-Horizon-MoVA-36B-A4B: hardware requirements
K2-Horizon-MoVA-36B-A4B needs about 25 GB of memory at Q4_K_M quantization: a 22 GB download plus room for context and a runtime allowance. That fits a machine with 32GB RAM.
This is a mixture-of-experts model. Only a fraction of its 37B 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 | 22 GB | 25 GB | 31 GB | IFM/K2-Horizon-MoVA-36B-A4B-GGUF |
| Q5_K_M | 26 GB | 30 GB | 36 GB | IFM/K2-Horizon-MoVA-36B-A4B-GGUF |
| Q6_K | 31 GB | 35 GB | 40 GB | IFM/K2-Horizon-MoVA-36B-A4B-GGUF |
| Q8_0 | 40 GB | 44 GB | 49 GB | IFM/K2-Horizon-MoVA-36B-A4B-GGUF |
| BF16 | 75 GB | 79 GB | 85 GB | IFM/K2-Horizon-MoVA-36B-A4B-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).