TEST #3360 RESULTS
04/21/2026 - 4:30 PM
ACCELERATOR
MODEL
77.2
tokens/s
generation
1.18
sec
time to first token
1086
tokens/s
prompt
414
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
Apple M4 4P+6E
RAM
16GB
OS
Darwin
Kernel Release
24.6.0
Architecture
arm64
Version
Cosmopolitan 3.9.7 MODE=aarch64; Darwin Kernel Version 24.6.0: Mon Jan 19 22:01:41 PST 2026; root:xnu-11417.140.69.708.3~1/RELEASE_ARM64_T8132
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
1335
tokens/s
84.7
tokens/s
779
ms
pp4096+tg256
979
tokens/s
55.7
tokens/s
4.20
sec
pp2048+tg256
1211
tokens/s
71.6
tokens/s
1.71
sec
pp2048+tg768
1199
tokens/s
69.1
tokens/s
1.72
sec
pp1024+tg1024
1307
tokens/s
79.0
tokens/s
795
ms
pp1280+tg3072
1291
tokens/s
65.2
tokens/s
1.00
sec
pp384+tg1152
1294
tokens/s
86.7
tokens/s
307
ms
pp64+tg1024
869
tokens/s
93.0
tokens/s
84
ms
pp16+tg1536
292
tokens/s
89.7
tokens/s
65
ms