TEST #2537 RESULTS
02/04/2026 - 10:57 PM
ACCELERATOR
MODEL
105
tokens/s
generation
445
ms
time to first token
3073
tokens/s
prompt
898
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q8_0
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
3885
tokens/s
130
tokens/s
271
ms
pp4096+tg256
2564
tokens/s
29.0
tokens/s
1.63
sec
pp2048+tg256
3170
tokens/s
91.6
tokens/s
657
ms
pp2048+tg768
3242
tokens/s
87.8
tokens/s
642
ms
pp1024+tg1024
3813
tokens/s
110
tokens/s
277
ms
pp1280+tg3072
3588
tokens/s
71.4
tokens/s
365
ms
pp384+tg1152
3975
tokens/s
133
tokens/s
103
ms
pp64+tg1024
1466
tokens/s
152
tokens/s
49
ms
pp16+tg1536
1957
tokens/s
142
tokens/s
13
ms