TEST #1153 RESULTS
06/29/2025 - 2:49 AM
ACCELERATOR
MODEL
75.2
tokens/s
generation
1.19
sec
time to first token
1113
tokens/s
prompt
413
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
24.2.0
Architecture
arm64
Version
Cosmopolitan 3.9.7 MODE=aarch64; Darwin Kernel Version 24.2.0: Fri Dec 6 19:04:03 PST 2024; root:xnu-11215.61.5~2/RELEASE_ARM64_T8132
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
1324
tokens/s
83.4
tokens/s
785
ms
pp4096+tg256
964
tokens/s
54.5
tokens/s
4.27
sec
pp2048+tg256
1197
tokens/s
70.1
tokens/s
1.72
sec
pp2048+tg768
1195
tokens/s
67.6
tokens/s
1.73
sec
pp1024+tg1024
1316
tokens/s
77.0
tokens/s
790
ms
pp1280+tg3072
1291
tokens/s
64.2
tokens/s
1.00
sec
pp384+tg1152
1343
tokens/s
84.4
tokens/s
297
ms
pp64+tg1024
1012
tokens/s
90.2
tokens/s
74
ms
pp16+tg1536
373
tokens/s
85.4
tokens/s
53
ms