TEST #487 RESULTS
04/07/2025 - 10:31 AM
ACCELERATOR
MODEL
25.5
tokens/s
generation
3.69
sec
time to first token
335
tokens/s
prompt
132
LocalScore
HOW YOU STACK UP
Explore All ResultsLLaMA v2 - Q8_0
SYSTEM
CPU
Apple M4 Pro 8P+4E
RAM
24GB
OS
Darwin
Kernel Release
24.4.0
Architecture
arm64
Version
Cosmopolitan 3.9.7 MODE=aarch64; Darwin Kernel Version 24.4.0: Wed Mar 19 21:17:35 PDT 2025; root:xnu-11417.101.15~1/RELEASE_ARM64_T6041
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
385
tokens/s
27.6
tokens/s
2.70
sec
pp4096+tg256
350
tokens/s
20.2
tokens/s
11.76
sec
pp2048+tg256
369
tokens/s
24.3
tokens/s
5.58
sec
pp2048+tg768
372
tokens/s
23.7
tokens/s
5.54
sec
pp1024+tg1024
383
tokens/s
26.0
tokens/s
2.71
sec
pp1280+tg3072
376
tokens/s
22.7
tokens/s
3.44
sec
pp384+tg1152
365
tokens/s
27.8
tokens/s
1.09
sec
pp64+tg1024
295
tokens/s
29.1
tokens/s
249
ms
pp16+tg1536
116
tokens/s
28.4
tokens/s
170
ms