Qwen3.5-122B-A10B: hardware requirements
Qwen3.5-122B-A10B needs about 82 GB of memory at Q4 quantization — a 78 GB download plus room for context and overhead. That fits a machine with 128GB RAM.
This is a mixture-of-experts model. Only a fraction of its 125B 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 | 78 GB | 82 GB | 85 GB | measured |
| Q5_K_M | 94 GB | 97 GB | 100 GB | measured |
| Q6_K | 104 GB | 108 GB | 111 GB | measured |
| Q8_0 | 133 GB | 136 GB | 139 GB | measured |
| BF16 | 250 GB | 254 GB | 257 GB | measured |
“Measured” sizes are read from published GGUF files (unsloth/Qwen3.5-122B-A10B-MTP-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.