TEST #1863 RESULTS
11/25/2025 - 8:09 AM
ACCELERATOR
MODEL
184
tokens/s
generation
227
ms
time to first token
5967
tokens/s
prompt
1693
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
Intel Xeon E-2144G CPU @ 3.60GHz (skylake)
RAM
62.7GB
OS
Linux
Kernel Release
6.14.0-36-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #36~24.04.1-Ubuntu SMP PREEMPT_DYNAMIC Wed Oct 15 15:45:17 UTC 2
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
7323
tokens/s
232
tokens/s
144
ms
pp4096+tg256
5169
tokens/s
142
tokens/s
799
ms
pp2048+tg256
6449
tokens/s
174
tokens/s
330
ms
pp2048+tg768
6460
tokens/s
166
tokens/s
330
ms
pp1024+tg1024
7238
tokens/s
183
tokens/s
146
ms
pp1280+tg3072
7110
tokens/s
160
tokens/s
185
ms
pp384+tg1152
7550
tokens/s
195
tokens/s
55
ms
pp64+tg1024
5688
tokens/s
206
tokens/s
25
ms
pp16+tg1536
713
tokens/s
199
tokens/s
26
ms