TEST #3878 RESULTS
07/08/2026 - 3:37 PM
ACCELERATOR
MODEL
22.9
tokens/s
generation
22.32
sec
time to first token
66
tokens/s
prompt
41
LocalScore
HOW YOU STACK UP
Explore All Results.. - Q4_0
SYSTEM
CPU
ARMv8 Processor rev 1 (v8l)
RAM
7.4GB
OS
Linux
Kernel Release
5.15.148-tegra
Architecture
aarch64
Version
Cosmopolitan 3.9.7 MODE=aarch64; #1 SMP PREEMPT Thu Sep 18 15:08:33 PDT 2025
RUNTIME
Name
llamafile
Version
0.9.3
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
68
tokens/s
26.6
tokens/s
15.15
sec
pp4096+tg256
54
tokens/s
18.1
tokens/s
76.28
sec
pp2048+tg256
58
tokens/s
19.1
tokens/s
35.53
sec
pp2048+tg768
62
tokens/s
18.7
tokens/s
33.04
sec
pp1024+tg1024
68
tokens/s
21.1
tokens/s
15.16
sec
pp1280+tg3072
66
tokens/s
20.0
tokens/s
19.32
sec
pp384+tg1152
73
tokens/s
26.7
tokens/s
5.28
sec
pp64+tg1024
77
tokens/s
28.2
tokens/s
864
ms
pp16+tg1536
72
tokens/s
27.3
tokens/s
254
ms