Alpamayo2-Super: hardware requirements
Alpamayo2-Super needs about 26 GB of memory at Q4 quantization — a 22 GB download plus room for context and overhead. That fits a machine with 64GB RAM.
Parameters
36B
Tier
Needs a good desktop
Licence
See model card
Released
2026-04-08
Will it run on your machine?
8GB RAMNot enough memory16GB RAMNot enough memory24GB RAMNot enough memory32GB RAMTight fit64GB RAMRuns well128GB RAMRuns well8GB VRAMNot enough memory12GB VRAMNot enough memory16GB VRAMNot enough memory24GB VRAMNot enough memory32GB 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?
| Quant | Download | RAM @ 4K | RAM @ 32K | Source |
|---|---|---|---|---|
| Q4_K_Mrecommended | 22 GB | 26 GB | 26 GB | estimated |
| Q5_K_M | 25 GB | 31 GB | 31 GB | estimated |
| Q6_K | 29 GB | 36 GB | 36 GB | estimated |
| Q8_0 | 38 GB | 46 GB | 46 GB | estimated |
| BF16 | 72 GB | 83 GB | 83 GB | estimated |
“Measured” sizes are read from published GGUF files. “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.
Model card on HuggingFace →API specs & pricing →Verified 2026-08-13Tracked for 12 months after release