TEST #1458 RESULTS
08/30/2025 - 9:45 AM
ACCELERATOR
MODEL
179
tokens/s
generation
209
ms
time to first token
5483
tokens/s
prompt
1674
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
Apple M3 Ultra 24P+8E
RAM
512GB
OS
Darwin
Kernel Release
24.6.0
Architecture
arm64
Version
Cosmopolitan 3.9.7 MODE=aarch64; Darwin Kernel Version 24.6.0: Mon Jul 14 11:30:55 PDT 2025; root:xnu-11417.140.69~1/RELEASE_ARM64_T6031
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
7204
tokens/s
197
tokens/s
147
ms
pp4096+tg256
6390
tokens/s
128
tokens/s
649
ms
pp2048+tg256
7061
tokens/s
167
tokens/s
296
ms
pp2048+tg768
7104
tokens/s
161
tokens/s
294
ms
pp1024+tg1024
6982
tokens/s
183
tokens/s
152
ms
pp1280+tg3072
6839
tokens/s
152
tokens/s
192
ms
pp384+tg1152
5611
tokens/s
200
tokens/s
73
ms
pp64+tg1024
1689
tokens/s
217
tokens/s
43
ms
pp16+tg1536
464
tokens/s
209
tokens/s
39
ms