TEST #936 RESULTS
05/23/2025 - 10:08 AM
ACCELERATOR
MODEL
59.5
tokens/s
generation
1.44
sec
time to first token
874
tokens/s
prompt
331
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
Apple M3 4P+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: Fri Apr 11 18:34:14 PDT 2025; root:xnu-11417.101.15~117/RELEASE_ARM64_T8122
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
1122
tokens/s
74.7
tokens/s
926
ms
pp4096+tg256
811
tokens/s
48.0
tokens/s
5.07
sec
pp2048+tg256
1021
tokens/s
62.3
tokens/s
2.02
sec
pp2048+tg768
1015
tokens/s
59.1
tokens/s
2.03
sec
pp1024+tg1024
1029
tokens/s
68.2
tokens/s
1.01
sec
pp1280+tg3072
995
tokens/s
57.7
tokens/s
1.30
sec
pp384+tg1152
946
tokens/s
62.5
tokens/s
421
ms
pp64+tg1024
674
tokens/s
53.1
tokens/s
107
ms
pp16+tg1536
254
tokens/s
50.0
tokens/s
76
ms