TEST #1470 RESULTS
09/03/2025 - 4:51 AM
ACCELERATOR
MODEL
25.1
tokens/s
generation
3.39
sec
time to first token
371
tokens/s
prompt
140
LocalScore
HOW YOU STACK UP
Explore All ResultsMeta Llama 3.1 8B Instruct - Q4_K - Medium
SYSTEM
CPU
Apple M3 Max 12P+4E
RAM
64GB
OS
Darwin
Kernel Release
23.6.0
Architecture
arm64
Version
Cosmopolitan 3.9.7 MODE=aarch64; Darwin Kernel Version 23.6.0: Thu Sep 12 23:36:23 PDT 2024; root:xnu-10063.141.1.701.1~1/RELEASE_ARM64_T6031
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
417
tokens/s
27.9
tokens/s
2.48
sec
pp4096+tg256
379
tokens/s
21.8
tokens/s
10.84
sec
pp2048+tg256
404
tokens/s
24.9
tokens/s
5.10
sec
pp2048+tg768
405
tokens/s
24.3
tokens/s
5.09
sec
pp1024+tg1024
413
tokens/s
25.7
tokens/s
2.51
sec
pp1280+tg3072
407
tokens/s
23.0
tokens/s
3.17
sec
pp384+tg1152
415
tokens/s
25.9
tokens/s
953
ms
pp64+tg1024
385
tokens/s
26.5
tokens/s
186
ms
pp16+tg1536
116
tokens/s
26.3
tokens/s
156
ms