TEST #1353 RESULTS
08/10/2025 - 9:27 AM
ACCELERATOR
MODEL
104
tokens/s
generation
80
ms
time to first token
16219
tokens/s
prompt
2762
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD Ryzen Threadripper PRO 7965WX 24-Cores (znver4)
RAM
251.2GB
OS
Linux
Kernel Release
6.8.0-71-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #71-Ubuntu SMP PREEMPT_DYNAMIC Tue Jul 22 16:52:38 UTC 2025
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
21684
tokens/s
113
tokens/s
56
ms
pp4096+tg256
18453
tokens/s
93.2
tokens/s
233
ms
pp2048+tg256
19942
tokens/s
110
tokens/s
112
ms
pp2048+tg768
20299
tokens/s
99.9
tokens/s
111
ms
pp1024+tg1024
21989
tokens/s
103
tokens/s
56
ms
pp1280+tg3072
19613
tokens/s
97.4
tokens/s
75
ms
pp384+tg1152
18925
tokens/s
106
tokens/s
29
ms
pp64+tg1024
3921
tokens/s
107
tokens/s
26
ms
pp16+tg1536
1144
tokens/s
106
tokens/s
23
ms