TEST #508 RESULTS
04/07/2025 - 6:37 PM
ACCELERATOR
MODEL
200
tokens/s
generation
101
ms
time to first token
15093
tokens/s
prompt
3099
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
13th Gen Intel Core i7-13700K (alderlake)
RAM
63.7GB
OS
Windows
Kernel Release
10.0
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
20069
tokens/s
215
tokens/s
56
ms
pp4096+tg256
10380
tokens/s
202
tokens/s
400
ms
pp2048+tg256
15144
tokens/s
197
tokens/s
140
ms
pp2048+tg768
15080
tokens/s
199
tokens/s
141
ms
pp1024+tg1024
19751
tokens/s
198
tokens/s
57
ms
pp1280+tg3072
18767
tokens/s
198
tokens/s
73
ms
pp384+tg1152
24893
tokens/s
198
tokens/s
20
ms
pp64+tg1024
9379
tokens/s
197
tokens/s
12
ms
pp16+tg1536
2372
tokens/s
195
tokens/s
12
ms