TEST #157 RESULTS
03/28/2025 - 11:09 PM
ACCELERATOR
MODEL
188
tokens/s
generation
177
ms
time to first token
8712
tokens/s
prompt
2098
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
Intel Xeon CPU E5-2690 v4 @ 2.60GHz (broadwell)
RAM
251.8GB
OS
Linux
Kernel Release
6.8.0-51-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #52-Ubuntu SMP PREEMPT_DYNAMIC Thu Dec 5 13:09:44 UTC 2024
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
10325
tokens/s
186
tokens/s
105
ms
pp4096+tg256
5883
tokens/s
167
tokens/s
703
ms
pp2048+tg256
8439
tokens/s
185
tokens/s
249
ms
pp2048+tg768
8436
tokens/s
183
tokens/s
249
ms
pp1024+tg1024
11019
tokens/s
192
tokens/s
99
ms
pp1280+tg3072
10222
tokens/s
176
tokens/s
131
ms
pp384+tg1152
15962
tokens/s
198
tokens/s
29
ms
pp64+tg1024
5983
tokens/s
202
tokens/s
16
ms
pp16+tg1536
2136
tokens/s
200
tokens/s
12
ms