TEST #3094 RESULTS
03/15/2026 - 2:49 PM
ACCELERATOR
MODEL
57.5
tokens/s
generation
838
ms
time to first token
1545
tokens/s
prompt
473
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
1542
tokens/s
59.9
tokens/s
681
ms
pp4096+tg256
1474
tokens/s
50.3
tokens/s
2.80
sec
pp2048+tg256
1694
tokens/s
56.4
tokens/s
1.23
sec
pp2048+tg768
1713
tokens/s
55.5
tokens/s
1.21
sec
pp1024+tg1024
1852
tokens/s
58.5
tokens/s
569
ms
pp1280+tg3072
1801
tokens/s
54.1
tokens/s
728
ms
pp384+tg1152
1929
tokens/s
60.4
tokens/s
216
ms
pp64+tg1024
1510
tokens/s
61.6
tokens/s
58
ms
pp16+tg1536
389
tokens/s
60.8
tokens/s
57
ms