TEST #718 RESULTS
04/14/2025 - 7:40 AM
ACCELERATOR
MODEL
168
tokens/s
generation
253
ms
time to first token
6085
tokens/s
prompt
1590
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD Ryzen 9 5900X 12-Core Processor (znver3)
RAM
47GB
OS
Linux
Kernel Release
6.13.10-200.fc41.x86_64
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #1 SMP PREEMPT_DYNAMIC Mon Apr 7 19:01:38 UTC 2025
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
7202
tokens/s
177
tokens/s
148
ms
pp4096+tg256
4179
tokens/s
142
tokens/s
987
ms
pp2048+tg256
5758
tokens/s
163
tokens/s
362
ms
pp2048+tg768
5754
tokens/s
160
tokens/s
362
ms
pp1024+tg1024
7008
tokens/s
171
tokens/s
152
ms
pp1280+tg3072
6683
tokens/s
155
tokens/s
197
ms
pp384+tg1152
9512
tokens/s
178
tokens/s
46
ms
pp64+tg1024
6423
tokens/s
183
tokens/s
16
ms
pp16+tg1536
2251
tokens/s
180
tokens/s
12
ms