TEST #3667 RESULTS
06/02/2026 - 6:16 AM
ACCELERATOR
MODEL
38.5
tokens/s
generation
13.23
sec
time to first token
109
tokens/s
prompt
68
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD Ryzen 5 2600 Six-Core Processor
RAM
15.5GB
OS
Linux
Kernel Release
7.0.10-201.fc44.x86_64
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #1 SMP PREEMPT_DYNAMIC Wed May 27 13:57:41 UTC 2026
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
104
tokens/s
41.5
tokens/s
9.85
sec
pp4096+tg256
91
tokens/s
30.3
tokens/s
44.90
sec
pp2048+tg256
104
tokens/s
37.0
tokens/s
19.72
sec
pp2048+tg768
104
tokens/s
35.9
tokens/s
19.74
sec
pp1024+tg1024
111
tokens/s
39.4
tokens/s
9.23
sec
pp1280+tg3072
110
tokens/s
34.1
tokens/s
11.66
sec
pp384+tg1152
118
tokens/s
42.3
tokens/s
3.29
sec
pp64+tg1024
123
tokens/s
43.7
tokens/s
542
ms
pp16+tg1536
117
tokens/s
42.0
tokens/s
158
ms