BackendROCm
Decode39.11 tok/s
Prompt eval474.36 tok/s
VRAM12 GB
Memory bandwidth~384 GB/s
ModelSpark-X2.5 4B
Parameters4.1B
QuantizationBF16
Context101K
KV quantf16
OffloadPartial (some layers in RAM)
About this result
Measured -p 512 -n 128 -r 3, per-test isolated telemetry (benchscope). Slowest and hottest (62 C); the only quant that failed the JSON quality task. Full weights: 7.66 GiB.
Status: Measured in the VelsTech Lab on real hardware. Read the full Lab report →