TEST #103 RESULTS
03/28/2025 - 9:39 PM
ACCELERATOR
MODEL
144
tokens/s
generation
320
ms
time to first token
4047
tokens/s
prompt
1221
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
Intel Xeon CPU E7-8867 v4 @ 2.40GHz (broadwell)
RAM
188.7GB
OS
Linux
Kernel Release
5.15.0-131-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #141~20.04.1-Ubuntu SMP Thu Jan 16 18:38:51 UTC 2025
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
5027
tokens/s
139
tokens/s
211
ms
pp4096+tg256
3701
tokens/s
100
tokens/s
1.12
sec
pp2048+tg256
4497
tokens/s
132
tokens/s
463
ms
pp2048+tg768
4464
tokens/s
130
tokens/s
466
ms
pp1024+tg1024
4985
tokens/s
151
tokens/s
212
ms
pp1280+tg3072
4634
tokens/s
122
tokens/s
283
ms
pp384+tg1152
5138
tokens/s
167
tokens/s
81
ms
pp64+tg1024
2898
tokens/s
180
tokens/s
27
ms
pp16+tg1536
1080
tokens/s
173
tokens/s
20
ms