TEST #1638 RESULTS
10/12/2025 - 1:11 AM
ACCELERATOR
MODEL
39.1
tokens/s
generation
1.91
sec
time to first token
632
tokens/s
prompt
235
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
Apple M2 4P+4E
RAM
8GB
OS
Darwin
Kernel Release
24.6.0
Architecture
arm64
Version
Cosmopolitan 3.9.7 MODE=aarch64; Darwin Kernel Version 24.6.0: Mon Jul 14 11:30:51 PDT 2025; root:xnu-11417.140.69~1/RELEASE_ARM64_T8112
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
818
tokens/s
58.3
tokens/s
1.27
sec
pp4096+tg256
631
tokens/s
32.6
tokens/s
6.52
sec
pp2048+tg256
754
tokens/s
46.6
tokens/s
2.74
sec
pp2048+tg768
764
tokens/s
43.8
tokens/s
2.70
sec
pp1024+tg1024
816
tokens/s
52.0
tokens/s
1.27
sec
pp1280+tg3072
806
tokens/s
29.7
tokens/s
1.61
sec
pp384+tg1152
529
tokens/s
27.9
tokens/s
749
ms
pp64+tg1024
420
tokens/s
33.3
tokens/s
172
ms
pp16+tg1536
152
tokens/s
27.3
tokens/s
146
ms