Meta Llama 3.1 8B

Q4_K_M running on AMD Radeon Vega ×6 + AMD Radeon Pro 580X with macOS 15.7.9 Sequoia

PERFORMANCE / TOKENS PER SECONDGCN / Vega

Prompt processing558.18tok/s

#117 in index

Token generation32.86tok/s

#156 in index

Run fingerprint

Enough context to make the number useful.

ModelMeta Llama 3.1 8BDense architecture

QuantizationQ4_K_MExact submitted variant

GPUAMD Radeon Vega ×6 + AMD Radeon Pro 580X103.91 GB VRAM

GPU architectureGCN / VegaMetal backend

Test context512prompt tokens

Model familyDenseSigned ToshLLM app · amd-gpu · Metal

ToshLLM versionv0.87.0App version used to capture and sign this run

Prompt processing and generation are reported separately so memory bandwidth and decode behavior stay visible.

Quantization, GPU family, VRAM and context travel with the result instead of being hidden behind one score.

This result remains explicitly labeled as a community submission.