TEST #2833 RESULTS
02/24/2026 - 4:38 AM
ACCELERATOR
MODEL
301
tokens/s
generation
72
ms
time to first token
21300
tokens/s
prompt
4465
LocalScore
HOW YOU STACK UP
Explore All ResultsGpt2 - 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
24840
tokens/s
298
tokens/s
45
ms
pp4096+tg256
14267
tokens/s
252
tokens/s
291
ms
pp2048+tg256
22189
tokens/s
289
tokens/s
96
ms
pp2048+tg768
22215
tokens/s
294
tokens/s
95
ms
pp1024+tg1024
27453
tokens/s
318
tokens/s
40
ms
pp1280+tg3072
25353
tokens/s
293
tokens/s
53
ms
pp384+tg1152
38718
tokens/s
326
tokens/s
12
ms
pp64+tg1024
13436
tokens/s
325
tokens/s
7
ms
pp16+tg1536
3231
tokens/s
315
tokens/s
8
ms