TEST #1084 RESULTS
06/20/2025 - 9:02 PM
ACCELERATOR
MODEL
37.7
tokens/s
generation
2.71
sec
time to first token
442
tokens/s
prompt
183
LocalScore
HOW YOU STACK UP
Explore All ResultsMeta Llama 3.1 8B Instruct - Q4_K - Medium
SYSTEM
CPU
Apple M3 Max 10P+4E
RAM
36GB
OS
Darwin
Kernel Release
24.5.0
Architecture
arm64
Version
Cosmopolitan 3.9.7 MODE=aarch64; Darwin Kernel Version 24.5.0: Tue Apr 22 19:52:00 PDT 2025; root:xnu-11417.121.6~2/RELEASE_ARM64_T6031
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
527
tokens/s
41.0
tokens/s
1.97
sec
pp4096+tg256
484
tokens/s
30.2
tokens/s
8.49
sec
pp2048+tg256
513
tokens/s
36.4
tokens/s
4.02
sec
pp2048+tg768
510
tokens/s
34.7
tokens/s
4.04
sec
pp1024+tg1024
523
tokens/s
38.9
tokens/s
1.98
sec
pp1280+tg3072
495
tokens/s
34.1
tokens/s
2.61
sec
pp384+tg1152
417
tokens/s
41.2
tokens/s
944
ms
pp64+tg1024
370
tokens/s
42.6
tokens/s
195
ms
pp16+tg1536
134
tokens/s
40.1
tokens/s
142
ms