TEST #1273 RESULTS
07/30/2025 - 2:33 PM
ACCELERATOR
MODEL
37.9
tokens/s
generation
989
ms
time to first token
1373
tokens/s
prompt
375
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
125.3GB
OS
Linux
Kernel Release
6.12.34-6.12-alt1
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #1 SMP PREEMPT_DYNAMIC Tue Jun 24 14:31:35 UTC 2025
RUNTIME
Name
llamafile
Version
0.9.3
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
1613
tokens/s
39.3
tokens/s
660
ms
pp4096+tg256
1229
tokens/s
34.5
tokens/s
3.36
sec
pp2048+tg256
1446
tokens/s
37.5
tokens/s
1.44
sec
pp2048+tg768
1438
tokens/s
37.0
tokens/s
1.45
sec
pp1024+tg1024
1571
tokens/s
38.3
tokens/s
677
ms
pp1280+tg3072
1419
tokens/s
36.1
tokens/s
928
ms
pp384+tg1152
1691
tokens/s
39.1
tokens/s
252
ms
pp64+tg1024
1454
tokens/s
39.8
tokens/s
69
ms
pp16+tg1536
496
tokens/s
39.4
tokens/s
56
ms