TEST #551 RESULTS
04/08/2025 - 1:58 AM
ACCELERATOR
MODEL
180
tokens/s
generation
314
ms
time to first token
3608
tokens/s
prompt
1273
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
24.4.0
Architecture
arm64
Version
Cosmopolitan 3.9.7 MODE=aarch64; Darwin Kernel Version 24.4.0: Wed Mar 19 21:17:35 PDT 2025; root:xnu-11417.101.15~1/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
204
tokens/s
212
ms
pp4096+tg256
4221
tokens/s
123
tokens/s
978
ms
pp2048+tg256
4588
tokens/s
163
tokens/s
452
ms
pp2048+tg768
4727
tokens/s
156
tokens/s
439
ms
pp1024+tg1024
4577
tokens/s
181
tokens/s
229
ms
pp1280+tg3072
4476
tokens/s
148
tokens/s
291
ms
pp384+tg1152
3301
tokens/s
204
tokens/s
121
ms
pp64+tg1024
1266
tokens/s
223
tokens/s
55
ms
pp16+tg1536
375
tokens/s
213
tokens/s
46
ms