TEST #62 RESULTS
03/28/2025 - 8:54 PM
ACCELERATOR
MODEL
173
tokens/s
generation
244
ms
time to first token
6151
tokens/s
prompt
1634
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD EPYC 7443 24-Core Processor (znver3)
RAM
251.5GB
OS
Linux
Kernel Release
6.8.0-49-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #49~22.04.1-Ubuntu SMP PREEMPT_DYNAMIC Wed Nov 6 17:42:15 UTC 2
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
7406
tokens/s
184
tokens/s
144
ms
pp4096+tg256
4376
tokens/s
147
tokens/s
943
ms
pp2048+tg256
6012
tokens/s
168
tokens/s
347
ms
pp2048+tg768
6009
tokens/s
165
tokens/s
347
ms
pp1024+tg1024
7380
tokens/s
176
tokens/s
144
ms
pp1280+tg3072
6916
tokens/s
160
tokens/s
191
ms
pp384+tg1152
9724
tokens/s
183
tokens/s
45
ms
pp64+tg1024
6573
tokens/s
189
tokens/s
15
ms
pp16+tg1536
962
tokens/s
185
tokens/s
22
ms