TEST #1178 RESULTS
07/04/2025 - 7:09 PM
ACCELERATOR
MODEL
122
tokens/s
generation
573
ms
time to first token
2134
tokens/s
prompt
769
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
Apple M4 Pro 10P+4E
RAM
48GB
OS
Darwin
Kernel Release
24.5.0
Architecture
arm64
Version
Cosmopolitan 3.9.7 MODE=aarch64; Darwin Kernel Version 24.5.0: Tue Apr 22 19:53:27 PDT 2025; root:xnu-11417.121.6~2/RELEASE_ARM64_T6041
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
2595
tokens/s
140
tokens/s
402
ms
pp4096+tg256
2146
tokens/s
78.6
tokens/s
1.92
sec
pp2048+tg256
2473
tokens/s
110
tokens/s
837
ms
pp2048+tg768
2471
tokens/s
104
tokens/s
838
ms
pp1024+tg1024
2589
tokens/s
125
tokens/s
403
ms
pp1280+tg3072
2556
tokens/s
97.5
tokens/s
508
ms
pp384+tg1152
2475
tokens/s
142
tokens/s
161
ms
pp64+tg1024
1450
tokens/s
156
tokens/s
50
ms
pp16+tg1536
456
tokens/s
148
tokens/s
40
ms