TEST #1179 RESULTS
07/04/2025 - 7:18 PM
ACCELERATOR
MODEL
32.7
tokens/s
generation
3.51
sec
time to first token
351
tokens/s
prompt
148
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
24.5.0
Architecture
arm64
Version
Cosmopolitan 3.9.7 MODE=aarch64; Darwin Kernel Version 24.5.0: Tue Apr 22 19:53:27 PDT 2025; root:xnu-11417.121.6~2/RELEASE_ARM64_T6041
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
415
tokens/s
36.7
tokens/s
2.50
sec
pp4096+tg256
377
tokens/s
25.7
tokens/s
10.89
sec
pp2048+tg256
400
tokens/s
31.6
tokens/s
5.15
sec
pp2048+tg768
377
tokens/s
30.9
tokens/s
5.47
sec
pp1024+tg1024
373
tokens/s
33.8
tokens/s
2.77
sec
pp1280+tg3072
380
tokens/s
29.4
tokens/s
3.39
sec
pp384+tg1152
377
tokens/s
35.3
tokens/s
1.05
sec
pp64+tg1024
338
tokens/s
36.3
tokens/s
213
ms
pp16+tg1536
121
tokens/s
35.0
tokens/s
158
ms