TEST #2536 RESULTS
02/04/2026 - 10:53 PM
ACCELERATOR
MODEL
112
tokens/s
generation
446
ms
time to first token
3009
tokens/s
prompt
911
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q6_K
SYSTEM
CPU
AMD Ryzen 7 5700G with Radeon Graphics (znver3)
RAM
27.3GB
OS
Linux
Kernel Release
6.17.12-300.fc43.x86_64
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #1 SMP PREEMPT_DYNAMIC Sat Dec 13 05:06:24 UTC 2025
RUNTIME
Name
llamafile
Version
0.9.3
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
3396
tokens/s
138
tokens/s
309
ms
pp4096+tg256
2580
tokens/s
29.6
tokens/s
1.62
sec
pp2048+tg256
3233
tokens/s
97.4
tokens/s
644
ms
pp2048+tg768
3245
tokens/s
92.3
tokens/s
641
ms
pp1024+tg1024
3849
tokens/s
118
tokens/s
273
ms
pp1280+tg3072
3616
tokens/s
74.4
tokens/s
362
ms
pp384+tg1152
3943
tokens/s
143
tokens/s
103
ms
pp64+tg1024
1427
tokens/s
166
tokens/s
50
ms
pp16+tg1536
1797
tokens/s
152
tokens/s
14
ms