TEST #1626 RESULTS
10/09/2025 - 3:14 PM
ACCELERATOR
MODEL
148
tokens/s
generation
371
ms
time to first token
2956
tokens/s
prompt
1057
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
3747
tokens/s
161
tokens/s
280
ms
pp4096+tg256
4009
tokens/s
113
tokens/s
1.03
sec
pp2048+tg256
4002
tokens/s
142
tokens/s
519
ms
pp2048+tg768
4099
tokens/s
136
tokens/s
507
ms
pp1024+tg1024
3695
tokens/s
152
tokens/s
283
ms
pp1280+tg3072
3824
tokens/s
130
tokens/s
341
ms
pp384+tg1152
2459
tokens/s
164
tokens/s
162
ms
pp64+tg1024
609
tokens/s
170
tokens/s
111
ms
pp16+tg1536
163
tokens/s
166
tokens/s
106
ms