TEST #813 RESULTS
05/04/2025 - 10:16 AM
ACCELERATOR
MODEL
32.1
tokens/s
generation
3.49
sec
time to first token
358
tokens/s
prompt
149
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
24.4.0
Architecture
arm64
Version
Cosmopolitan 3.9.7 MODE=aarch64; Darwin Kernel Version 24.4.0: Fri Apr 11 18:32:50 PDT 2025; root:xnu-11417.101.15~117/RELEASE_ARM64_T6041
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
408
tokens/s
35.3
tokens/s
2.54
sec
pp4096+tg256
367
tokens/s
24.4
tokens/s
11.19
sec
pp2048+tg256
396
tokens/s
30.6
tokens/s
5.21
sec
pp2048+tg768
390
tokens/s
29.9
tokens/s
5.29
sec
pp1024+tg1024
398
tokens/s
33.1
tokens/s
2.60
sec
pp1280+tg3072
395
tokens/s
28.4
tokens/s
3.27
sec
pp384+tg1152
411
tokens/s
35.5
tokens/s
962
ms
pp64+tg1024
330
tokens/s
36.6
tokens/s
219
ms
pp16+tg1536
127
tokens/s
34.8
tokens/s
151
ms