TEST #3172 RESULTS
03/23/2026 - 8:56 PM
ACCELERATOR
MODEL
78.1
tokens/s
generation
1.16
sec
time to first token
1126
tokens/s
prompt
423
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
25.3.0
Architecture
arm64
Version
Cosmopolitan 3.9.7 MODE=aarch64; Darwin Kernel Version 25.3.0: Wed Jan 28 20:54:55 PST 2026; root:xnu-12377.91.3~2/RELEASE_ARM64_T8132
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
1345
tokens/s
84.5
tokens/s
773
ms
pp4096+tg256
1000
tokens/s
56.5
tokens/s
4.11
sec
pp2048+tg256
1226
tokens/s
72.7
tokens/s
1.68
sec
pp2048+tg768
1229
tokens/s
70.2
tokens/s
1.68
sec
pp1024+tg1024
1342
tokens/s
80.2
tokens/s
774
ms
pp1280+tg3072
1320
tokens/s
66.3
tokens/s
982
ms
pp384+tg1152
1347
tokens/s
88.0
tokens/s
295
ms
pp64+tg1024
1049
tokens/s
93.9
tokens/s
71
ms
pp16+tg1536
276
tokens/s
90.7
tokens/s
68
ms