M3 Max qwen-2-5-14b-instruct Q4_K - Medium TTFT (llamafile, siliconscore ref)
5407.046111222224 ms (time to first token)
Fields
id
benchmarks/m3max-qwen-2-5-14b-instruct-q4-k-medium-llamafile-ctxnp-ttftMetric
ttft_ms
Value
5,407.0461
Unit
ms (time to first token)
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. TTFT seconds.
Measured by
third_party
Reproducible
yes
Thermal state
unknown
notes
siliconscore reference run; source_url=https://www.localscore.ai/accelerator/805.
Notes
siliconscore reference run; source_url=https://www.localscore.ai/accelerator/805.