#38 in index
Community submission
Performance record · Dense
Meta Llama 3.1 8B
Q4_K_M running on AMD Radeon Vega + AMD Radeon Vega + AMD Radeon Vega + AMD Radeon Vega + AMD Radeon PRO W6800X Duo + AMD Radeon PRO W6800X Duo + AMD Radeon PRO W6800X Duo + AMD
PERFORMANCE / TOKENS PER SECONDGCN / Vega + RDNA 2
#47 in index
Run fingerprint
Enough context to make the number useful.
01
Standard workload
Prompt processing and generation are reported separately so memory bandwidth and decode behavior stay visible.
02
Configuration attached
Quantization, GPU family, VRAM and context travel with the result instead of being hidden behind one score.
03
Provenance preserved
This result remains explicitly labeled as a community submission.