TEST #1420 RESULTS
08/24/2025 - 12:53 PM
ACCELERATOR
MODEL
54.2
tokens/s
generation
421
ms
time to first token
3200
tokens/s
prompt
744
LocalScore
HOW YOU STACK UP
Explore All ResultsMinistral 8B Instruct 2410 TEST - Q6_K
SYSTEM
CPU
AMD Ryzen 9 3900X 12-Core Processor (znver2)
RAM
31.3GB
OS
Linux
Kernel Release
6.16.1-arch1-1
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #1 SMP PREEMPT_DYNAMIC Fri, 15 Aug 2025 16:04:43 +0000
RUNTIME
Name
llamafile
Version
0.9.3
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
3821
tokens/s
55.3
tokens/s
288
ms
pp4096+tg256
2768
tokens/s
50.3
tokens/s
1.50
sec
pp2048+tg256
3512
tokens/s
53.5
tokens/s
602
ms
pp2048+tg768
3528
tokens/s
53.2
tokens/s
599
ms
pp1024+tg1024
4091
tokens/s
55.0
tokens/s
268
ms
pp1280+tg3072
3969
tokens/s
53.0
tokens/s
341
ms
pp384+tg1152
4638
tokens/s
55.7
tokens/s
101
ms
pp64+tg1024
1784
tokens/s
56.2
tokens/s
53
ms
pp16+tg1536
691
tokens/s
56.0
tokens/s
40
ms