TEST #1642 RESULTS
10/13/2025 - 11:43 AM
ACCELERATOR
MODEL
4.8
tokens/s
generation
7.47
sec
time to first token
280
tokens/s
prompt
56
LocalScore
HOW YOU STACK UP
Explore All ResultsMeta Llama 3.1 8B Instruct - Q4_K - Medium
SYSTEM
CPU
13th Gen Intel Core i7-13700H (alderlake)
RAM
15.5GB
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
0.9.3
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
174
tokens/s
5.5
tokens/s
6.05
sec
pp4096+tg256
98
tokens/s
2.2
tokens/s
42.45
sec
pp2048+tg256
430
tokens/s
5.6
tokens/s
4.94
sec
pp2048+tg768
414
tokens/s
5.4
tokens/s
5.13
sec
pp1024+tg1024
427
tokens/s
5.4
tokens/s
2.58
sec
pp1280+tg3072
367
tokens/s
4.6
tokens/s
3.70
sec
pp384+tg1152
368
tokens/s
4.7
tokens/s
1.25
sec
pp64+tg1024
193
tokens/s
4.8
tokens/s
542
ms
pp16+tg1536
45
tokens/s
4.7
tokens/s
565
ms