TEST #2452 RESULTS
02/01/2026 - 5:56 AM
ACCELERATOR
MODEL
379
tokens/s
generation
26
ms
time to first token
55309
tokens/s
prompt
9296
LocalScore
HOW YOU STACK UP
Explore All ResultsAMD Llama 135m - 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
72672
tokens/s
372
tokens/s
17
ms
pp4096+tg256
42179
tokens/s
365
tokens/s
101
ms
pp2048+tg256
78822
tokens/s
382
tokens/s
28
ms
pp2048+tg768
73839
tokens/s
372
tokens/s
30
ms
pp1024+tg1024
72330
tokens/s
373
tokens/s
17
ms
pp1280+tg3072
79788
tokens/s
377
tokens/s
18
ms
pp384+tg1152
61267
tokens/s
382
tokens/s
9
ms
pp64+tg1024
13511
tokens/s
401
tokens/s
7
ms
pp16+tg1536
3371
tokens/s
385
tokens/s
7
ms