TEST #1506 RESULTS
09/11/2025 - 10:09 PM
ACCELERATOR
MODEL
342
tokens/s
generation
93
ms
time to first token
14411
tokens/s
prompt
3755
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD Ryzen Threadripper PRO 3945WX 12-Cores (znver2)
RAM
125.6GB
OS
Linux
Kernel Release
6.12.46-1-lts
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #1 SMP PREEMPT_DYNAMIC Tue, 09 Sep 2025 18:30:25 +0000
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
17449
tokens/s
338
tokens/s
62
ms
pp4096+tg256
12331
tokens/s
294
tokens/s
336
ms
pp2048+tg256
15981
tokens/s
338
tokens/s
131
ms
pp2048+tg768
15885
tokens/s
333
tokens/s
132
ms
pp1024+tg1024
18700
tokens/s
351
tokens/s
58
ms
pp1280+tg3072
17205
tokens/s
321
tokens/s
77
ms
pp384+tg1152
20073
tokens/s
358
tokens/s
22
ms
pp64+tg1024
10218
tokens/s
375
tokens/s
9
ms
pp16+tg1536
1855
tokens/s
369
tokens/s
11
ms