TEST #2414 RESULTS
01/31/2026 - 6:42 AM
ACCELERATOR
MODEL
45.2
tokens/s
generation
830
ms
time to first token
1763
tokens/s
prompt
458
LocalScore
HOW YOU STACK UP
Explore All ResultsDistilGPT OSS Qwen3 4B - 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
2041
tokens/s
48.8
tokens/s
522
ms
pp4096+tg256
1357
tokens/s
40.1
tokens/s
3.04
sec
pp2048+tg256
1722
tokens/s
44.6
tokens/s
1.21
sec
pp2048+tg768
1728
tokens/s
43.8
tokens/s
1.21
sec
pp1024+tg1024
1987
tokens/s
46.0
tokens/s
536
ms
pp1280+tg3072
1952
tokens/s
42.4
tokens/s
677
ms
pp384+tg1152
2522
tokens/s
45.8
tokens/s
172
ms
pp64+tg1024
1889
tokens/s
47.2
tokens/s
53
ms
pp16+tg1536
667
tokens/s
48.0
tokens/s
45
ms