TEST #1567 RESULTS
09/27/2025 - 4:03 PM
ACCELERATOR
MODEL
32.8
tokens/s
generation
3.38
sec
time to first token
369
tokens/s
prompt
153
LocalScore
HOW YOU STACK UP
Explore All ResultsMeta Llama 3.1 8B Instruct - Q4_K - Medium
SYSTEM
CPU
Apple M4 Pro 10P+4E
RAM
48GB
OS
Darwin
Kernel Release
25.0.0
Architecture
arm64
Version
Cosmopolitan 3.9.7 MODE=aarch64; Darwin Kernel Version 25.0.0: Mon Aug 25 21:17:54 PDT 2025; root:xnu-12377.1.9~3/RELEASE_ARM64_T6041
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
418
tokens/s
35.9
tokens/s
2.48
sec
pp4096+tg256
381
tokens/s
25.2
tokens/s
10.80
sec
pp2048+tg256
404
tokens/s
31.1
tokens/s
5.10
sec
pp2048+tg768
406
tokens/s
30.2
tokens/s
5.08
sec
pp1024+tg1024
417
tokens/s
33.5
tokens/s
2.48
sec
pp1280+tg3072
407
tokens/s
29.0
tokens/s
3.17
sec
pp384+tg1152
401
tokens/s
36.0
tokens/s
984
ms
pp64+tg1024
350
tokens/s
37.8
tokens/s
208
ms
pp16+tg1536
140
tokens/s
36.9
tokens/s
139
ms