TEST #1759 RESULTS
11/08/2025 - 4:00 PM
ACCELERATOR
MODEL
190
tokens/s
generation
2.82
sec
time to first token
8921
tokens/s
prompt
843
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
Intel Xeon Gold 6138 CPU @ 2.00GHz (skylake-avx512)
RAM
93GB
OS
Linux
Kernel Release
6.14.0-35-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #35~24.04.1-Ubuntu SMP PREEMPT_DYNAMIC Tue Oct 14 13:55:17 UTC 2
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
11696
tokens/s
211
tokens/s
92
ms
pp4096+tg256
6497
tokens/s
127
tokens/s
638
ms
pp2048+tg256
9108
tokens/s
172
tokens/s
231
ms
pp2048+tg768
9103
tokens/s
165
tokens/s
231
ms
pp1024+tg1024
11575
tokens/s
194
tokens/s
93
ms
pp1280+tg3072
10786
tokens/s
155
tokens/s
124
ms
pp384+tg1152
14433
tokens/s
218
tokens/s
31
ms
pp64+tg1024
7089
tokens/s
238
tokens/s
13
ms
pp16+tg1536
1
tokens/s
227
tokens/s
23.93
sec