TEST #2810 RESULTS
02/23/2026 - 10:22 AM
ACCELERATOR
MODEL
34.8
tokens/s
generation
676
ms
time to first token
2042
tokens/s
prompt
472
LocalScore
HOW YOU STACK UP
Explore All ResultsMeta Llama 3.1 8B Instruct - Q4_K - Medium
SYSTEM
CPU
RAM
119.6GB
OS
Linux
Kernel Release
6.17.0-1008-nvidia
Architecture
aarch64
Version
Cosmopolitan 3.9.7 MODE=aarch64; #8-Ubuntu SMP PREEMPT_DYNAMIC Wed Jan 21 17:56:56 UTC 2026
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
2482
tokens/s
35.1
tokens/s
442
ms
pp4096+tg256
1714
tokens/s
32.0
tokens/s
2.42
sec
pp2048+tg256
2192
tokens/s
34.5
tokens/s
964
ms
pp2048+tg768
2180
tokens/s
34.1
tokens/s
970
ms
pp1024+tg1024
2525
tokens/s
35.3
tokens/s
435
ms
pp1280+tg3072
2414
tokens/s
33.6
tokens/s
559
ms
pp384+tg1152
2930
tokens/s
36.0
tokens/s
159
ms
pp64+tg1024
1504
tokens/s
36.6
tokens/s
71
ms
pp16+tg1536
439
tokens/s
36.3
tokens/s
65
ms