TEST #809 RESULTS
05/04/2025 - 9:53 AM
ACCELERATOR
MODEL
78.1
tokens/s
generation
1.01
sec
time to first token
1190
tokens/s
prompt
452
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
Apple M1 Pro 8P+2E
RAM
32GB
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 18:33:47 PDT 2025; root:xnu-11417.101.15~117/RELEASE_ARM64_T6000
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
1457
tokens/s
87.6
tokens/s
714
ms
pp4096+tg256
1243
tokens/s
52.4
tokens/s
3.31
sec
pp2048+tg256
1385
tokens/s
71.0
tokens/s
1.49
sec
pp2048+tg768
1404
tokens/s
67.9
tokens/s
1.47
sec
pp1024+tg1024
1451
tokens/s
79.7
tokens/s
717
ms
pp1280+tg3072
1427
tokens/s
63.8
tokens/s
909
ms
pp384+tg1152
1358
tokens/s
89.6
tokens/s
293
ms
pp64+tg1024
745
tokens/s
97.7
tokens/s
95
ms
pp16+tg1536
239
tokens/s
93.1
tokens/s
76
ms