TEST #2571 RESULTS
02/10/2026 - 9:01 AM
ACCELERATOR
MODEL
280
tokens/s
generation
71
ms
time to first token
21889
tokens/s
prompt
4423
LocalScore
HOW YOU STACK UP
Explore All ResultsMiniPLM Qwen 200M - Q6_K
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
26695
tokens/s
269
tokens/s
43
ms
pp4096+tg256
16586
tokens/s
252
tokens/s
255
ms
pp2048+tg256
21805
tokens/s
283
tokens/s
97
ms
pp2048+tg768
24002
tokens/s
278
tokens/s
90
ms
pp1024+tg1024
31674
tokens/s
290
tokens/s
36
ms
pp1280+tg3072
27480
tokens/s
273
tokens/s
50
ms
pp384+tg1152
36261
tokens/s
292
tokens/s
14
ms
pp64+tg1024
10120
tokens/s
295
tokens/s
43
ms
pp16+tg1536
2382
tokens/s
289
tokens/s
10
ms