TEST #2426 RESULTS
01/31/2026 - 3:40 PM
ACCELERATOR
MODEL
79.0
tokens/s
generation
351
ms
time to first token
4600
tokens/s
prompt
1011
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen3 Coder 0.6B 0.9B 7 1bR5 Nobs F16 - 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
5893
tokens/s
84.4
tokens/s
187
ms
pp4096+tg256
2887
tokens/s
69.3
tokens/s
1.43
sec
pp2048+tg256
4340
tokens/s
79.5
tokens/s
486
ms
pp2048+tg768
4286
tokens/s
77.6
tokens/s
491
ms
pp1024+tg1024
5601
tokens/s
82.0
tokens/s
196
ms
pp1280+tg3072
5191
tokens/s
75.6
tokens/s
258
ms
pp384+tg1152
7979
tokens/s
81.2
tokens/s
59
ms
pp64+tg1024
4072
tokens/s
83.0
tokens/s
26
ms
pp16+tg1536
1153
tokens/s
78.9
tokens/s
25
ms