TEST #4109 RESULTS
09/01/2026 - 8:22 AM
ACCELERATOR
MODEL
68.2
tokens/s
generation
244
ms
time to first token
4928
tokens/s
prompt
1113
LocalScore
HOW YOU STACK UP
Explore All ResultsMeta Llama 3.1 8B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD Ryzen Threadripper 9960X 24-Cores
RAM
125.2GB
OS
Linux
Kernel Release
6.8.0-136-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #136-Ubuntu SMP PREEMPT_DYNAMIC Wed Jul 1 21:53:05 UTC 2026
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
5822
tokens/s
77.2
tokens/s
189
ms
pp4096+tg256
5455
tokens/s
42.4
tokens/s
774
ms
pp2048+tg256
6677
tokens/s
57.7
tokens/s
324
ms
pp2048+tg768
6777
tokens/s
56.1
tokens/s
319
ms
pp1024+tg1024
7875
tokens/s
68.5
tokens/s
143
ms
pp1280+tg3072
5854
tokens/s
54.2
tokens/s
232
ms
pp384+tg1152
4098
tokens/s
82.3
tokens/s
104
ms
pp64+tg1024
919
tokens/s
90.1
tokens/s
80
ms
pp16+tg1536
873
tokens/s
85.1
tokens/s
29
ms