M3 Max qwen-2-5-14b-instruct Q4_K - Medium decode (llamafile, siliconscore ref)
19.768525888888888 tok/s (single-request decode, per-request)
Fields
id
benchmarks/m3max-qwen-2-5-14b-instruct-q4-k-medium-llamafile-ctxnp-tgMetric
decode_tok_s
Value
19.7685
Unit
tok/s (single-request decode, per-request)
Model
qwen-2-5-14b-instruct
Methodology
Silicon Score benchmarks.csv reference run. M3 Max (30-core GPU, 36 GB): qwen-2-5-14b-instruct Q4_K - Medium via llamafile. context_tokens=not published. Decode tok/s single-request.
Measured by
third_party
Reproducible
yes
Thermal state
unknown
notes
siliconscore reference run; source_url=https://www.localscore.ai/accelerator/805. Chip variant 'M3 Max (30-core GPU, 36 GB)'.
Notes
siliconscore reference run; source_url=https://www.localscore.ai/accelerator/805. Chip variant 'M3 Max (30-core GPU, 36 GB)'.