TEST #2506 RESULTS
02/01/2026 - 11:19 PM
ACCELERATOR
MODEL
78.5
tokens/s
generation
331
ms
time to first token
4527
tokens/s
prompt
1024
LocalScore
HOW YOU STACK UP
Explore All ResultsSailor2 1B Chat - Q4_K - Medium
SYSTEM
CPU
Intel Core i5-14450HX (alderlake)
RAM
15.7GB
OS
Windows
Kernel Release
10.0
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64
RUNTIME
Name
llamafile
Version
0.9.3
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
6180
tokens/s
79.1
tokens/s
179
ms
pp4096+tg256
3291
tokens/s
74.1
tokens/s
1.26
sec
pp2048+tg256
4647
tokens/s
75.8
tokens/s
453
ms
pp2048+tg768
4655
tokens/s
74.0
tokens/s
452
ms
pp1024+tg1024
5835
tokens/s
76.9
tokens/s
188
ms
pp1280+tg3072
5413
tokens/s
74.4
tokens/s
251
ms
pp384+tg1152
7699
tokens/s
84.7
tokens/s
62
ms
pp64+tg1024
2311
tokens/s
81.8
tokens/s
98
ms
pp16+tg1536
711
tokens/s
85.9
tokens/s
37
ms