TEST #1631 RESULTS
10/10/2025 - 12:48 PM
ACCELERATOR
MODEL
154
tokens/s
generation
364
ms
time to first token
2998
tokens/s
prompt
1082
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
25.0.0
Architecture
arm64
Version
Cosmopolitan 3.9.7 MODE=aarch64; Darwin Kernel Version 25.0.0: Wed Sep 17 21:41:45 PDT 2025; root:xnu-12377.1.9~141/RELEASE_ARM64_T6000
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
3821
tokens/s
165
tokens/s
274
ms
pp4096+tg256
4117
tokens/s
118
tokens/s
1.00
sec
pp2048+tg256
4143
tokens/s
145
tokens/s
501
ms
pp2048+tg768
4139
tokens/s
140
tokens/s
502
ms
pp1024+tg1024
3647
tokens/s
158
tokens/s
287
ms
pp1280+tg3072
3833
tokens/s
135
tokens/s
340
ms
pp384+tg1152
2486
tokens/s
170
tokens/s
160
ms
pp64+tg1024
634
tokens/s
179
tokens/s
106
ms
pp16+tg1536
161
tokens/s
174
tokens/s
104
ms