TEST #186 RESULTS
04/03/2025 - 5:14 PM
ACCELERATOR
MODEL
40.1
tokens/s
generation
7.10
sec
time to first token
195
tokens/s
prompt
103
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
Intel Xeon CPU E5-2697 v2 @ 2.70GHz (ivybridge)
RAM
251.8GB
OS
Linux
Kernel Release
6.11.0-14-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #15-Ubuntu SMP PREEMPT_DYNAMIC Fri Jan 10 23:48:25 UTC 2025
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
174
tokens/s
41.3
tokens/s
5.92
sec
pp4096+tg256
173
tokens/s
34.8
tokens/s
23.73
sec
pp2048+tg256
196
tokens/s
39.0
tokens/s
10.49
sec
pp2048+tg768
198
tokens/s
38.4
tokens/s
10.38
sec
pp1024+tg1024
209
tokens/s
40.8
tokens/s
4.92
sec
pp1280+tg3072
207
tokens/s
37.4
tokens/s
6.21
sec
pp384+tg1152
212
tokens/s
42.2
tokens/s
1.83
sec
pp64+tg1024
218
tokens/s
43.6
tokens/s
316
ms
pp16+tg1536
173
tokens/s
43.0
tokens/s
115
ms