TEST #1271 RESULTS
07/30/2025 - 2:16 PM
ACCELERATOR
MODEL
35.8
tokens/s
generation
1.07
sec
time to first token
1271
tokens/s
prompt
349
LocalScore
HOW YOU STACK UP
Explore All ResultsYandexGPT 5 Lite 8B Instruct - Q4_K - Medium
SYSTEM
CPU
11th Gen Intel Core i7-11700 @ 2.50GHz (rocketlake)
RAM
125.3GB
OS
Linux
Kernel Release
6.12.34-6.12-alt1
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #1 SMP PREEMPT_DYNAMIC Tue Jun 24 14:31:35 UTC 2025
RUNTIME
Name
llamafile
Version
0.9.3
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
1482
tokens/s
37.2
tokens/s
721
ms
pp4096+tg256
1117
tokens/s
32.4
tokens/s
3.69
sec
pp2048+tg256
1365
tokens/s
35.4
tokens/s
1.53
sec
pp2048+tg768
1297
tokens/s
35.2
tokens/s
1.61
sec
pp1024+tg1024
1473
tokens/s
36.2
tokens/s
725
ms
pp1280+tg3072
1407
tokens/s
34.1
tokens/s
936
ms
pp384+tg1152
1592
tokens/s
37.1
tokens/s
266
ms
pp64+tg1024
1328
tokens/s
37.7
tokens/s
73
ms
pp16+tg1536
376
tokens/s
37.2
tokens/s
69
ms