TEST #137 RESULTS
03/28/2025 - 10:17 PM
ACCELERATOR
MODEL
190
tokens/s
generation
208
ms
time to first token
7201
tokens/s
prompt
1874
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
Intel Xeon CPU E5-2699 v4 @ 2.20GHz (broadwell)
RAM
1007.7GB
OS
Linux
Kernel Release
6.8.0-52-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #53~22.04.1-Ubuntu SMP PREEMPT_DYNAMIC Wed Jan 15 19:18:46 UTC 2
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
8841
tokens/s
201
tokens/s
121
ms
pp4096+tg256
5255
tokens/s
160
tokens/s
786
ms
pp2048+tg256
7247
tokens/s
185
tokens/s
288
ms
pp2048+tg768
7248
tokens/s
182
tokens/s
288
ms
pp1024+tg1024
8856
tokens/s
194
tokens/s
121
ms
pp1280+tg3072
8360
tokens/s
176
tokens/s
158
ms
pp384+tg1152
11744
tokens/s
203
tokens/s
37
ms
pp64+tg1024
6977
tokens/s
208
tokens/s
14
ms
pp16+tg1536
280
tokens/s
205
tokens/s
62
ms