TEST #1339 RESULTS
08/08/2025 - 5:07 AM
ACCELERATOR
MODEL
179
tokens/s
generation
308
ms
time to first token
3756
tokens/s
prompt
1297
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
4937
tokens/s
201
tokens/s
212
ms
pp4096+tg256
4202
tokens/s
123
tokens/s
983
ms
pp2048+tg256
4615
tokens/s
162
tokens/s
450
ms
pp2048+tg768
4734
tokens/s
156
tokens/s
439
ms
pp1024+tg1024
4628
tokens/s
182
tokens/s
226
ms
pp1280+tg3072
4876
tokens/s
147
tokens/s
268
ms
pp384+tg1152
3964
tokens/s
204
tokens/s
101
ms
pp64+tg1024
1458
tokens/s
222
tokens/s
48
ms
pp16+tg1536
390
tokens/s
212
tokens/s
45
ms