Can I run a huge MoE model on a GB10?
Can I run a huge MoE model on a GB10?
Rentable machine
dgx-spark
Can I run a huge MoE model on a GB10?
Possibly. MoE models can be much larger on paper than the number of parameters actually used for each token.
That is one of the more interesting GB10 use cases: the 128 GB pool can hold large quantized weights, while only a subset of experts are active during generation.
The exact answer still depends on the model, quantization and serving engine. AxForge lists community GB10 results for MoE models well above 100B total parameters.
Sign in to reply.
Posting guidelines
Accounts that break these can lose forum access — paid plans included. Read the full guidelines →
Related topics