TEST #1907 RESULTS
12/03/2025 - 9:01 PM
ACCELERATOR
MODEL
32.5
tokens/s
generation
3.41
sec
time to first token
358
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
24GB
OS
Darwin
Kernel Release
25.1.0
Architecture
arm64
Version
Cosmopolitan 3.9.7 MODE=aarch64; Darwin Kernel Version 25.1.0: Mon Oct 20 19:34:05 PDT 2025; root:xnu-12377.41.6~2/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
36.3
tokens/s
2.48
sec
pp4096+tg256
382
tokens/s
25.3
tokens/s
10.77
sec
pp2048+tg256
406
tokens/s
31.2
tokens/s
5.08
sec
pp2048+tg768
406
tokens/s
30.3
tokens/s
5.08
sec
pp1024+tg1024
414
tokens/s
33.6
tokens/s
2.50
sec
pp1280+tg3072
405
tokens/s
28.6
tokens/s
3.19
sec
pp384+tg1152
337
tokens/s
33.8
tokens/s
1.17
sec
pp64+tg1024
327
tokens/s
36.6
tokens/s
220
ms
pp16+tg1536
124
tokens/s
36.6
tokens/s
153
ms