TEST #2453 RESULTS
02/01/2026 - 5:56 AM
ACCELERATOR
MODEL
378
tokens/s
generation
27
ms
time to first token
52402
tokens/s
prompt
9048
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
63899
tokens/s
353
tokens/s
19
ms
pp4096+tg256
42092
tokens/s
351
tokens/s
101
ms
pp2048+tg256
76605
tokens/s
342
tokens/s
29
ms
pp2048+tg768
67587
tokens/s
383
tokens/s
33
ms
pp1024+tg1024
82446
tokens/s
382
tokens/s
15
ms
pp1280+tg3072
65344
tokens/s
366
tokens/s
22
ms
pp384+tg1152
56989
tokens/s
384
tokens/s
9
ms
pp64+tg1024
13028
tokens/s
448
tokens/s
7
ms
pp16+tg1536
3628
tokens/s
395
tokens/s
7
ms