TEST #399 RESULTS
04/06/2025 - 5:19 PM
ACCELERATOR
MODEL
137
tokens/s
generation
425
ms
time to first token
2586
tokens/s
prompt
941
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
24.3.0
Architecture
arm64
Version
Cosmopolitan 3.9.7 MODE=aarch64; Darwin Kernel Version 24.3.0: Thu Jan 2 20:24:16 PST 2025; root:xnu-11215.81.4~3/RELEASE_ARM64_T6000
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
3308
tokens/s
149
tokens/s
316
ms
pp4096+tg256
3404
tokens/s
103
tokens/s
1.21
sec
pp2048+tg256
3458
tokens/s
129
tokens/s
600
ms
pp2048+tg768
3504
tokens/s
125
tokens/s
592
ms
pp1024+tg1024
3341
tokens/s
141
tokens/s
313
ms
pp1280+tg3072
3313
tokens/s
118
tokens/s
393
ms
pp384+tg1152
2164
tokens/s
152
tokens/s
184
ms
pp64+tg1024
614
tokens/s
161
tokens/s
111
ms
pp16+tg1536
166
tokens/s
157
tokens/s
103
ms