TEST #112 RESULTS
03/28/2025 - 9:50 PM
ACCELERATOR
MODEL
242
tokens/s
generation
153
ms
time to first token
8708
tokens/s
prompt
2396
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD Ryzen 5 3600 6-Core Processor (znver2)
RAM
62.7GB
OS
Linux
Kernel Release
6.5.0-21-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #21~22.04.1-Ubuntu SMP PREEMPT_DYNAMIC Fri Feb 9 13:32:52 UTC 2
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
11194
tokens/s
265
tokens/s
95
ms
pp4096+tg256
7396
tokens/s
182
tokens/s
559
ms
pp2048+tg256
9610
tokens/s
227
tokens/s
218
ms
pp2048+tg768
9615
tokens/s
220
tokens/s
217
ms
pp1024+tg1024
11158
tokens/s
246
tokens/s
96
ms
pp1280+tg3072
10538
tokens/s
211
tokens/s
125
ms
pp384+tg1152
10839
tokens/s
269
tokens/s
39
ms
pp64+tg1024
7010
tokens/s
286
tokens/s
12
ms
pp16+tg1536
1016
tokens/s
276
tokens/s
19
ms