TEST #3608 RESULTS
05/25/2026 - 2:29 PM
ACCELERATOR
MODEL
212
tokens/s
generation
213
ms
time to first token
6082
tokens/s
prompt
1821
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
Intel Xeon CPU E5-2660 v3 @ 2.60GHz (haswell)
RAM
247.5GB
OS
Linux
Kernel Release
7.0.0-15-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #15-Ubuntu SMP PREEMPT_DYNAMIC Wed Apr 22 16:06:43 UTC 2026
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
7765
tokens/s
233
tokens/s
136
ms
pp4096+tg256
5442
tokens/s
163
tokens/s
759
ms
pp2048+tg256
6776
tokens/s
199
tokens/s
308
ms
pp2048+tg768
6944
tokens/s
194
tokens/s
300
ms
pp1024+tg1024
7727
tokens/s
216
tokens/s
137
ms
pp1280+tg3072
7377
tokens/s
186
tokens/s
178
ms
pp384+tg1152
7974
tokens/s
233
tokens/s
53
ms
pp64+tg1024
4136
tokens/s
245
tokens/s
19
ms
pp16+tg1536
599
tokens/s
238
tokens/s
31
ms