TEST #1520 RESULTS
09/15/2025 - 10:59 AM
ACCELERATOR
MODEL
82.8
tokens/s
generation
280
ms
time to first token
4888
tokens/s
prompt
1130
LocalScore
HOW YOU STACK UP
Explore All ResultsMeta Llama 3.1 8B Instruct - Q4_K - Medium
SYSTEM
CPU
13th Gen Intel Core i9-13900K (alderlake)
RAM
31.2GB
OS
Linux
Kernel Release
6.6.87.2-microsoft-standard-WSL2
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #1 SMP PREEMPT_DYNAMIC Thu Jun 5 18:30:46 UTC 2025
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
6167
tokens/s
81.9
tokens/s
178
ms
pp4096+tg256
4196
tokens/s
76.8
tokens/s
990
ms
pp2048+tg256
5199
tokens/s
79.2
tokens/s
407
ms
pp2048+tg768
4879
tokens/s
79.9
tokens/s
432
ms
pp1024+tg1024
6159
tokens/s
84.3
tokens/s
178
ms
pp1280+tg3072
6329
tokens/s
83.1
tokens/s
214
ms
pp384+tg1152
6833
tokens/s
86.0
tokens/s
68
ms
pp64+tg1024
3223
tokens/s
85.9
tokens/s
31
ms
pp16+tg1536
1008
tokens/s
88.3
tokens/s
27
ms