TEST #1788 RESULTS
11/13/2025 - 5:47 AM
ACCELERATOR
MODEL
178
tokens/s
generation
203
ms
time to first token
5719
tokens/s
prompt
1713
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
Apple M3 Ultra 24P+8E
RAM
512GB
OS
Darwin
Kernel Release
25.1.0
Architecture
arm64
Version
Cosmopolitan 3.9.7 MODE=aarch64; Darwin Kernel Version 25.1.0: Mon Oct 20 19:30:01 PDT 2025; root:xnu-12377.41.6~2/RELEASE_ARM64_T6031
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
7530
tokens/s
198
tokens/s
141
ms
pp4096+tg256
6505
tokens/s
128
tokens/s
637
ms
pp2048+tg256
7198
tokens/s
165
tokens/s
291
ms
pp2048+tg768
7172
tokens/s
159
tokens/s
292
ms
pp1024+tg1024
7256
tokens/s
183
tokens/s
146
ms
pp1280+tg3072
7327
tokens/s
151
tokens/s
180
ms
pp384+tg1152
6069
tokens/s
200
tokens/s
68
ms
pp64+tg1024
1917
tokens/s
216
tokens/s
38
ms
pp16+tg1536
500
tokens/s
206
tokens/s
36
ms