TEST #2493 RESULTS
02/01/2026 - 10:47 AM
ACCELERATOR
MODEL
260
tokens/s
generation
173
ms
time to first token
10922
tokens/s
prompt
2539
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 2 Tiny 4kv Heads 16layers Random - 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
11040
tokens/s
306
tokens/s
96
ms
pp4096+tg256
5325
tokens/s
227
tokens/s
774
ms
pp2048+tg256
8998
tokens/s
254
tokens/s
232
ms
pp2048+tg768
9000
tokens/s
261
tokens/s
231
ms
pp1024+tg1024
13602
tokens/s
257
tokens/s
79
ms
pp1280+tg3072
11976
tokens/s
249
tokens/s
111
ms
pp384+tg1152
27467
tokens/s
261
tokens/s
17
ms
pp64+tg1024
8092
tokens/s
262
tokens/s
12
ms
pp16+tg1536
2796
tokens/s
263
tokens/s
9
ms