TEST #3135 RESULTS
03/20/2026 - 6:09 PM
ACCELERATOR
MODEL
53.3
tokens/s
generation
855
ms
time to first token
1520
tokens/s
prompt
456
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD Phenom(tm) 9550 Quad-Core Processor (amdfam10)
RAM
3.6GB
OS
Linux
Kernel Release
6.8.0-101-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #101-Ubuntu SMP PREEMPT_DYNAMIC Mon Feb 9 10:15:05 UTC 2026
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
1851
tokens/s
53.5
tokens/s
572
ms
pp4096+tg256
1385
tokens/s
37.9
tokens/s
2.98
sec
pp2048+tg256
1672
tokens/s
49.5
tokens/s
1.24
sec
pp2048+tg768
1672
tokens/s
47.9
tokens/s
1.25
sec
pp1024+tg1024
1842
tokens/s
55.3
tokens/s
573
ms
pp1280+tg3072
1772
tokens/s
45.4
tokens/s
740
ms
pp384+tg1152
1915
tokens/s
61.3
tokens/s
215
ms
pp64+tg1024
1155
tokens/s
66.0
tokens/s
69
ms
pp16+tg1536
417
tokens/s
63.4
tokens/s
52
ms