TEST #340 RESULTS
04/06/2025 - 1:45 AM
ACCELERATOR
MODEL
23.8
tokens/s
generation
2.06
sec
time to first token
647
tokens/s
prompt
195
LocalScore
HOW YOU STACK UP
Explore All ResultsMistral Nemo Instruct 2407 - Q6_K
SYSTEM
CPU
AMD Ryzen 9 5950X 16-Core Processor (znver3)
RAM
125.7GB
OS
Linux
Kernel Release
6.13.9-200.fc41.x86_64
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #1 SMP PREEMPT_DYNAMIC Sat Mar 29 01:29:31 UTC 2025
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
827
tokens/s
28.9
tokens/s
1.27
sec
pp4096+tg256
573
tokens/s
5.0
tokens/s
7.34
sec
pp2048+tg256
639
tokens/s
23.2
tokens/s
3.25
sec
pp2048+tg768
735
tokens/s
22.1
tokens/s
2.83
sec
pp1024+tg1024
818
tokens/s
26.0
tokens/s
1.29
sec
pp1280+tg3072
805
tokens/s
15.9
tokens/s
1.63
sec
pp384+tg1152
531
tokens/s
29.3
tokens/s
752
ms
pp64+tg1024
585
tokens/s
32.5
tokens/s
137
ms
pp16+tg1536
307
tokens/s
31.2
tokens/s
79
ms