TEST #4137 RESULTS
09/09/2026 - 4:11 PM
ACCELERATOR
MODEL
41.1
tokens/s
generation
142
ms
time to first token
9514
tokens/s
prompt
1401
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD Ryzen Threadripper 7960X 24-Cores (znver4)
RAM
94.3GB
OS
Linux
Kernel Release
6.18.40.1-microsoft-standard-WSL2
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #1 SMP PREEMPT_DYNAMIC Fri Jul 31 22:12:15 UTC 2026
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
12689
tokens/s
40.2
tokens/s
104
ms
pp4096+tg256
11993
tokens/s
39.5
tokens/s
366
ms
pp2048+tg256
12202
tokens/s
40.9
tokens/s
197
ms
pp2048+tg768
12077
tokens/s
41.1
tokens/s
194
ms
pp1024+tg1024
13243
tokens/s
40.7
tokens/s
101
ms
pp1280+tg3072
10973
tokens/s
40.5
tokens/s
142
ms
pp384+tg1152
10329
tokens/s
41.9
tokens/s
61
ms
pp64+tg1024
1697
tokens/s
42.8
tokens/s
57
ms
pp16+tg1536
417
tokens/s
42.2
tokens/s
58
ms