lhl/ggerganov: NVIDIA DGX Spark GB10 CUDA CUDA gpt-oss-120b tg32 52.87 t/s @0
52.87 tok/s per-request decode (batch 1, depth 0)
Fields
id
benchmarks/lhl-dgx-spark-gpt-oss-120b-cuda-tg32-d0Metric
decode_tok_s
Value
52.87
Unit
tok/s per-request decode (batch 1, depth 0)
Model
gpt-oss-120b MXFP4/Q8 GGUF
Methodology
THIRD-PARTY MEASURED (lhl/strix-halo-testing README). llama.cpp build 6792; gpt-oss-120b (ggml-org MXFP4/Q8); pp2048/tg32 vs depth 0-32768. Spark numbers from ggerganov's llama.cpp discussion #16578 sweep (b6767); Strix Halo numbers lhl on Framework Desktop, TheRock/ROCm 7.10.0a20251017. Per-request batch-1. NVIDIA DGX Spark GB10 CUDA
Measured by
third_party
Reproducible
yes