Xing4.0-29B-A4B: hardware requirements

Xing4.0-29B-A4B needs about 23 GB of memory at Q4 quantization — a 19 GB download plus room for context and overhead. That fits a machine with 32GB RAM.

Parameters
31B
Tier
Needs a good desktop
Licence
See model card
Released
2026-09-16

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?

QuantDownloadRAM @ 4KRAM @ 32KSource
Q4_K_Mrecommended19 GB23 GB40 GBestimated
Q5_K_M22 GB27 GB43 GBestimated
Q6_K26 GB31 GB47 GBestimated
Q8_033 GB39 GB55 GBestimated
BF1662 GB68 GB84 GBestimated

“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 2026-09-26Listed for 120 days after release