TEST #3434 RESULTS
05/03/2026 - 11:07 PM
ACCELERATOR
MODEL
23.0
tokens/s
generation
2.82
sec
time to first token
507
tokens/s
prompt
161
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen2.5.1 Coder 7B Instruct - Q6_K
SYSTEM
CPU
AMD Ryzen 7 5700G with Radeon Graphics (znver3)
RAM
15GB
OS
Linux
Kernel Release
6.19.13-arch1-1
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #1 SMP PREEMPT_DYNAMIC Tue, 21 Apr 2026 23:38:22 +0000
RUNTIME
Name
llamafile
Version
0.9.3
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
559
tokens/s
28.1
tokens/s
1.87
sec
pp4096+tg256
397
tokens/s
5.1
tokens/s
10.50
sec
pp2048+tg256
520
tokens/s
22.8
tokens/s
3.98
sec
pp2048+tg768
512
tokens/s
21.8
tokens/s
4.04
sec
pp1024+tg1024
589
tokens/s
25.6
tokens/s
1.77
sec
pp1280+tg3072
573
tokens/s
16.0
tokens/s
2.27
sec
pp384+tg1152
589
tokens/s
28.1
tokens/s
683
ms
pp64+tg1024
517
tokens/s
30.5
tokens/s
153
ms
pp16+tg1536
310
tokens/s
29.4
tokens/s
81
ms