01 // Inference benchmarks
Single-stream decode · llama.cpp
# env llama.cpp b4732 · 4096 ctx · batch=1 · prompt=512 · temp=0.0 · median of 5 runs
02 // Hardware specs
ArchitectureXe2-HPG
Process nodeTSMC 4nm
Memory12 GB
Memory bandwidth456 GB/s
FP16 compute14.6 TFLOPS
INT8 compute29 TOPS
TDP190 W
PCIeGen 4 x8
Form factorDual-slot
CoolingAxial
03 // Model fit
Approximate VRAM required to load weights + 4096 ctx KV cache.
+ STRENGTHS
- ✓12GB VRAM is enough for 32B-class models at Q4
- ✓456 GB/s memory bandwidth · top tier in its class
- ✓Strong tooling: FP16, Q8, Q4 all officially supported
− TRADE-OFFS
- −Draws 190W under load — plan PSU and thermals accordingly
- −Limited to dual-slot chassis
- −Driver lock-in to vendor stack