TEST #440 RESULTS
04/06/2025 - 11:08 PM
ACCELERATOR
MODEL
138
tokens/s
generation
432
ms
time to first token
2537
tokens/s
prompt
932
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
Apple M1 Ultra 16P+4E
RAM
128GB
OS
Darwin
Kernel Release
23.6.0
Architecture
arm64
Version
Cosmopolitan 3.9.7 MODE=aarch64; Darwin Kernel Version 23.6.0: Thu Dec 19 20:44:10 PST 2024; root:xnu-10063.141.1.703.2~1/RELEASE_ARM64_T6000
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
3418
tokens/s
152
tokens/s
306
ms
pp4096+tg256
3441
tokens/s
102
tokens/s
1.20
sec
pp2048+tg256
3572
tokens/s
129
tokens/s
581
ms
pp2048+tg768
3530
tokens/s
124
tokens/s
588
ms
pp1024+tg1024
3253
tokens/s
141
tokens/s
322
ms
pp1280+tg3072
3228
tokens/s
119
tokens/s
403
ms
pp384+tg1152
1823
tokens/s
153
tokens/s
217
ms
pp64+tg1024
406
tokens/s
162
tokens/s
163
ms
pp16+tg1536
163
tokens/s
157
tokens/s
104
ms