TEST #1060 RESULTS
06/15/2025 - 2:18 AM
ACCELERATOR
MODEL
20.1
tokens/s
generation
2.84
sec
time to first token
442
tokens/s
prompt
146
LocalScore
HOW YOU STACK UP
Explore All ResultsDeepSeek R1 Distill Qwen 14B - Q4_K - Medium
SYSTEM
CPU
AMD FX(tm)-8320 Eight-Core Processor (bdver2)
RAM
7.5GB
OS
Linux
Kernel Release
5.14.0-570.21.1.el9_6.x86_64
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #1 SMP PREEMPT_DYNAMIC Tue Jun 10 18:07:35 UTC 2025
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
521
tokens/s
20.5
tokens/s
2.02
sec
pp4096+tg256
446
tokens/s
15.9
tokens/s
9.25
sec
pp2048+tg256
490
tokens/s
19.3
tokens/s
4.23
sec
pp2048+tg768
488
tokens/s
18.9
tokens/s
4.25
sec
pp1024+tg1024
513
tokens/s
20.8
tokens/s
2.04
sec
pp1280+tg3072
495
tokens/s
18.0
tokens/s
2.63
sec
pp384+tg1152
518
tokens/s
22.1
tokens/s
783
ms
pp64+tg1024
397
tokens/s
23.2
tokens/s
201
ms
pp16+tg1536
113
tokens/s
22.5
tokens/s
182
ms