TEST #1340 RESULTS
08/08/2025 - 5:12 AM
ACCELERATOR
MODEL
178
tokens/s
generation
312
ms
time to first token
3658
tokens/s
prompt
1278
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
Apple M4 Max 12P+4E
RAM
48GB
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
4957
tokens/s
198
tokens/s
211
ms
pp4096+tg256
4198
tokens/s
122
tokens/s
984
ms
pp2048+tg256
4642
tokens/s
162
tokens/s
447
ms
pp2048+tg768
4642
tokens/s
156
tokens/s
447
ms
pp1024+tg1024
4502
tokens/s
181
tokens/s
232
ms
pp1280+tg3072
4579
tokens/s
147
tokens/s
285
ms
pp384+tg1152
3694
tokens/s
204
tokens/s
108
ms
pp64+tg1024
1279
tokens/s
222
tokens/s
54
ms
pp16+tg1536
426
tokens/s
211
tokens/s
41
ms