TEST #3093 RESULTS
03/15/2026 - 2:44 PM
ACCELERATOR
MODEL
52.8
tokens/s
generation
867
ms
time to first token
1502
tokens/s
prompt
450
LocalScore
HOW YOU STACK UP
Explore All ResultsMeta Llama 3.1 8B Instruct - Q4_K - Medium
SYSTEM
CPU
11th Gen Intel Core i7-11700 @ 2.50GHz (rocketlake)
RAM
2.9GB
OS
Linux
Kernel Release
6.12.73+deb13-amd64
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #1 SMP PREEMPT_DYNAMIC Debian 6.12.73-1 (2026-02-17)
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
1483
tokens/s
54.9
tokens/s
708
ms
pp4096+tg256
1418
tokens/s
46.7
tokens/s
2.91
sec
pp2048+tg256
1653
tokens/s
51.7
tokens/s
1.26
sec
pp2048+tg768
1656
tokens/s
51.1
tokens/s
1.26
sec
pp1024+tg1024
1809
tokens/s
53.5
tokens/s
584
ms
pp1280+tg3072
1752
tokens/s
49.9
tokens/s
749
ms
pp384+tg1152
1877
tokens/s
55.1
tokens/s
223
ms
pp64+tg1024
1498
tokens/s
56.4
tokens/s
60
ms
pp16+tg1536
376
tokens/s
55.7
tokens/s
60
ms