TEST #1629 RESULTS
10/09/2025 - 5:54 PM
ACCELERATOR
MODEL
180
tokens/s
generation
308
ms
time to first token
3751
tokens/s
prompt
1300
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
25.0.0
Architecture
arm64
Version
Cosmopolitan 3.9.7 MODE=aarch64; Darwin Kernel Version 25.0.0: Mon Aug 25 21:17:54 PDT 2025; root:xnu-12377.1.9~3/RELEASE_ARM64_T6041
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
5097
tokens/s
200
tokens/s
206
ms
pp4096+tg256
4249
tokens/s
124
tokens/s
972
ms
pp2048+tg256
4651
tokens/s
163
tokens/s
446
ms
pp2048+tg768
4695
tokens/s
157
tokens/s
442
ms
pp1024+tg1024
4661
tokens/s
183
tokens/s
225
ms
pp1280+tg3072
4727
tokens/s
148
tokens/s
276
ms
pp384+tg1152
4167
tokens/s
207
tokens/s
96
ms
pp64+tg1024
1160
tokens/s
225
tokens/s
60
ms
pp16+tg1536
356
tokens/s
214
tokens/s
49
ms