TEST #4277 RESULTS
10/13/2026 - 11:45 AM
ACCELERATOR
MODEL
110
tokens/s
generation
290
ms
time to first token
4555
tokens/s
prompt
1200
LocalScore
HOW YOU STACK UP
Explore All ResultsMeta Llama 3.1 8B Instruct - Q4_K - Medium
SYSTEM
CPU
Intel Core Ultra 9 275HX (arrowlake-s)
RAM
93.7GB
OS
Linux
Kernel Release
7.2.9-201.fc44.x86_64
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #1 SMP PREEMPT_DYNAMIC Fri Oct 9 15:04:46 UTC 2026
RUNTIME
Name
llamafile
Version
0.9.3
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
5456
tokens/s
115
tokens/s
196
ms
pp4096+tg256
4169
tokens/s
96.3
tokens/s
994
ms
pp2048+tg256
4951
tokens/s
107
tokens/s
422
ms
pp2048+tg768
4894
tokens/s
106
tokens/s
427
ms
pp1024+tg1024
5450
tokens/s
111
tokens/s
196
ms
pp1280+tg3072
5262
tokens/s
104
tokens/s
252
ms
pp384+tg1152
5876
tokens/s
115
tokens/s
74
ms
pp64+tg1024
3494
tokens/s
118
tokens/s
26
ms
pp16+tg1536
1448
tokens/s
116
tokens/s
18
ms