TEST #3472 RESULTS
05/08/2026 - 5:10 AM
ACCELERATOR
MODEL
322
tokens/s
generation
109
ms
time to first token
12425
tokens/s
prompt
3318
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD Ryzen 5 5600G with Radeon Graphics (znver3)
RAM
7.2GB
OS
Linux
Kernel Release
6.12.85+deb13-amd64
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #1 SMP PREEMPT_DYNAMIC Debian 6.12.85-1 (2026-04-30)
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
15827
tokens/s
337
tokens/s
68
ms
pp4096+tg256
10501
tokens/s
275
tokens/s
394
ms
pp2048+tg256
13613
tokens/s
314
tokens/s
154
ms
pp2048+tg768
13555
tokens/s
307
tokens/s
154
ms
pp1024+tg1024
15905
tokens/s
325
tokens/s
67
ms
pp1280+tg3072
14941
tokens/s
303
tokens/s
89
ms
pp384+tg1152
17252
tokens/s
339
tokens/s
25
ms
pp64+tg1024
9522
tokens/s
351
tokens/s
9
ms
pp16+tg1536
712
tokens/s
346
tokens/s
25
ms