TEST #1134 RESULTS
06/27/2025 - 1:35 AM
ACCELERATOR
MODEL
181
tokens/s
generation
303
ms
time to first token
3877
tokens/s
prompt
1324
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
Apple M4 Max 12P+4E
RAM
128GB
OS
Darwin
Kernel Release
24.5.0
Architecture
arm64
Version
Cosmopolitan 3.9.7 MODE=aarch64; Darwin Kernel Version 24.5.0: Tue Apr 22 19:53:27 PDT 2025; root:xnu-11417.121.6~2/RELEASE_ARM64_T6041
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
4942
tokens/s
203
tokens/s
212
ms
pp4096+tg256
4237
tokens/s
124
tokens/s
975
ms
pp2048+tg256
4733
tokens/s
166
tokens/s
439
ms
pp2048+tg768
4754
tokens/s
159
tokens/s
436
ms
pp1024+tg1024
4829
tokens/s
185
tokens/s
217
ms
pp1280+tg3072
4662
tokens/s
148
tokens/s
280
ms
pp384+tg1152
4315
tokens/s
206
tokens/s
93
ms
pp64+tg1024
1907
tokens/s
228
tokens/s
37
ms
pp16+tg1536
513
tokens/s
214
tokens/s
35
ms