TEST #2954 RESULTS
03/02/2026 - 12:22 PM
ACCELERATOR
MODEL
74.8
tokens/s
generation
415
ms
time to first token
3079
tokens/s
prompt
822
LocalScore
HOW YOU STACK UP
Explore All ResultsMeta Llama 3.1 8B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD Ryzen Threadripper PRO 5945WX 12-Cores (znver3)
RAM
127.9GB
OS
Windows
Kernel Release
10.0
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64
RUNTIME
Name
llamafile
Version
0.9.3
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
3633
tokens/s
75.8
tokens/s
295
ms
pp4096+tg256
2993
tokens/s
69.3
tokens/s
1.38
sec
pp2048+tg256
3472
tokens/s
73.9
tokens/s
604
ms
pp2048+tg768
3467
tokens/s
72.9
tokens/s
604
ms
pp1024+tg1024
3724
tokens/s
75.0
tokens/s
288
ms
pp1280+tg3072
3580
tokens/s
72.3
tokens/s
371
ms
pp384+tg1152
3693
tokens/s
75.9
tokens/s
118
ms
pp64+tg1024
2493
tokens/s
77.8
tokens/s
39
ms
pp16+tg1536
660
tokens/s
80.7
tokens/s
36
ms