TEST #163 RESULTS
03/30/2025 - 7:43 PM
ACCELERATOR
MODEL
275
tokens/s
generation
56
ms
time to first token
27681
tokens/s
prompt
5136
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD Ryzen 9 3900X 12-Core Processor (znver2)
RAM
125.7GB
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
39015
tokens/s
320
tokens/s
29
ms
pp4096+tg256
23005
tokens/s
173
tokens/s
184
ms
pp2048+tg256
32049
tokens/s
249
tokens/s
68
ms
pp2048+tg768
31927
tokens/s
231
tokens/s
68
ms
pp1024+tg1024
38867
tokens/s
277
tokens/s
30
ms
pp1280+tg3072
34901
tokens/s
216
tokens/s
40
ms
pp384+tg1152
37116
tokens/s
318
tokens/s
13
ms
pp64+tg1024
11998
tokens/s
354
tokens/s
8
ms
pp16+tg1536
255
tokens/s
333
tokens/s
65
ms