TEST #1665 RESULTS
10/18/2025 - 1:26 AM
ACCELERATOR
MODEL
177
tokens/s
generation
307
ms
time to first token
3800
tokens/s
prompt
1299
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
Apple M4 Max 12P+4E
RAM
64GB
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 11:30:40 PDT 2025; root:xnu-11417.140.69~1/RELEASE_ARM64_T6041
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
5041
tokens/s
198
tokens/s
208
ms
pp4096+tg256
4199
tokens/s
122
tokens/s
984
ms
pp2048+tg256
4653
tokens/s
160
tokens/s
446
ms
pp2048+tg768
4626
tokens/s
155
tokens/s
449
ms
pp1024+tg1024
5028
tokens/s
181
tokens/s
208
ms
pp1280+tg3072
4591
tokens/s
146
tokens/s
284
ms
pp384+tg1152
4134
tokens/s
202
tokens/s
97
ms
pp64+tg1024
1483
tokens/s
221
tokens/s
47
ms
pp16+tg1536
441
tokens/s
211
tokens/s
40
ms