TEST #1363 RESULTS
08/12/2025 - 3:40 PM
ACCELERATOR
MODEL
32.6
tokens/s
generation
3.41
sec
time to first token
362
tokens/s
prompt
151
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
24.6.0
Architecture
arm64
Version
Cosmopolitan 3.9.7 MODE=aarch64; Darwin Kernel Version 24.6.0: Mon Jul 14 11:30:40 PDT 2025; root:xnu-11417.140.69~1/RELEASE_ARM64_T6041
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
414
tokens/s
35.4
tokens/s
2.50
sec
pp4096+tg256
379
tokens/s
25.0
tokens/s
10.85
sec
pp2048+tg256
402
tokens/s
30.8
tokens/s
5.12
sec
pp2048+tg768
402
tokens/s
30.0
tokens/s
5.12
sec
pp1024+tg1024
410
tokens/s
33.4
tokens/s
2.52
sec
pp1280+tg3072
408
tokens/s
28.9
tokens/s
3.17
sec
pp384+tg1152
403
tokens/s
35.7
tokens/s
980
ms
pp64+tg1024
325
tokens/s
37.5
tokens/s
223
ms
pp16+tg1536
119
tokens/s
36.5
tokens/s
159
ms