TEST #840 RESULTS
05/07/2025 - 6:55 PM
ACCELERATOR
MODEL
44.8
tokens/s
generation
621
ms
time to first token
2217
tokens/s
prompt
543
LocalScore
HOW YOU STACK UP
Explore All ResultsMeta Llama 3.1 8B Instruct - Q4_K - Medium
SYSTEM
CPU
11th Gen Intel Core i7-11700F @ 2.50GHz (rocketlake)
RAM
31.9GB
OS
Windows
Kernel Release
10.0
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
2661
tokens/s
45.7
tokens/s
407
ms
pp4096+tg256
1877
tokens/s
42.5
tokens/s
2.21
sec
pp2048+tg256
2335
tokens/s
44.8
tokens/s
900
ms
pp2048+tg768
2339
tokens/s
44.5
tokens/s
899
ms
pp1024+tg1024
2660
tokens/s
45.4
tokens/s
408
ms
pp1280+tg3072
2595
tokens/s
41.6
tokens/s
515
ms
pp384+tg1152
3042
tokens/s
45.8
tokens/s
149
ms
pp64+tg1024
1872
tokens/s
46.3
tokens/s
56
ms
pp16+tg1536
572
tokens/s
46.1
tokens/s
50
ms