TEST #3192 RESULTS
03/25/2026 - 10:56 AM
ACCELERATOR
MODEL
135
tokens/s
generation
222
ms
time to first token
6980
tokens/s
prompt
1618
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
RAM
121.6GB
OS
Linux
Kernel Release
6.17.0-1014-nvidia
Architecture
aarch64
Version
Cosmopolitan 3.9.7 MODE=aarch64; #14-Ubuntu SMP PREEMPT_DYNAMIC Tue Mar 17 19:01:40 UTC 2026
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
8810
tokens/s
137
tokens/s
124
ms
pp4096+tg256
4636
tokens/s
117
tokens/s
894
ms
pp2048+tg256
6876
tokens/s
130
tokens/s
306
ms
pp2048+tg768
6755
tokens/s
128
tokens/s
312
ms
pp1024+tg1024
8890
tokens/s
137
tokens/s
124
ms
pp1280+tg3072
8220
tokens/s
126
tokens/s
163
ms
pp384+tg1152
11963
tokens/s
144
tokens/s
39
ms
pp64+tg1024
5174
tokens/s
148
tokens/s
19
ms
pp16+tg1536
1499
tokens/s
145
tokens/s
18
ms