TEST #2309 RESULTS
01/16/2026 - 2:43 AM
ACCELERATOR
MODEL
174
tokens/s
generation
335
ms
time to first token
3290
tokens/s
prompt
1196
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
Apple M2 Ultra 16P+8E
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 11:30:30 PDT 2025; root:xnu-11417.140.69~1/RELEASE_ARM64_T6020
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
4311
tokens/s
191
tokens/s
243
ms
pp4096+tg256
4299
tokens/s
126
tokens/s
961
ms
pp2048+tg256
4509
tokens/s
163
tokens/s
460
ms
pp2048+tg768
4424
tokens/s
157
tokens/s
469
ms
pp1024+tg1024
4079
tokens/s
178
tokens/s
256
ms
pp1280+tg3072
4107
tokens/s
149
tokens/s
317
ms
pp384+tg1152
2928
tokens/s
195
tokens/s
136
ms
pp64+tg1024
757
tokens/s
208
tokens/s
89
ms
pp16+tg1536
198
tokens/s
201
tokens/s
86
ms