TEST #2390 RESULTS
01/30/2026 - 2:39 PM
ACCELERATOR
MODEL
145
tokens/s
generation
121
ms
time to first token
13269
tokens/s
prompt
2514
LocalScore
HOW YOU STACK UP
Explore All ResultsSmolLM2 135M Instruct - 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
18264
tokens/s
137
tokens/s
63
ms
pp4096+tg256
8112
tokens/s
138
tokens/s
512
ms
pp2048+tg256
13523
tokens/s
146
tokens/s
161
ms
pp2048+tg768
13578
tokens/s
145
tokens/s
159
ms
pp1024+tg1024
20279
tokens/s
145
tokens/s
57
ms
pp1280+tg3072
17956
tokens/s
147
tokens/s
78
ms
pp384+tg1152
20588
tokens/s
148
tokens/s
26
ms
pp64+tg1024
5633
tokens/s
146
tokens/s
17
ms
pp16+tg1536
1493
tokens/s
152
tokens/s
17
ms