TEST #3431 RESULTS
05/03/2026 - 10:00 PM
ACCELERATOR
MODEL
26.4
tokens/s
generation
2.74
sec
time to first token
671
tokens/s
prompt
186
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen3 4B Instruct 2507 - Q4_K - Medium
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
786
tokens/s
35.8
tokens/s
1.33
sec
pp4096+tg256
343
tokens/s
3.0
tokens/s
12.27
sec
pp2048+tg256
560
tokens/s
22.2
tokens/s
3.70
sec
pp2048+tg768
560
tokens/s
20.1
tokens/s
3.70
sec
pp1024+tg1024
785
tokens/s
27.8
tokens/s
1.33
sec
pp1280+tg3072
735
tokens/s
12.0
tokens/s
1.77
sec
pp384+tg1152
979
tokens/s
35.5
tokens/s
414
ms
pp64+tg1024
806
tokens/s
41.9
tokens/s
98
ms
pp16+tg1536
483
tokens/s
39.0
tokens/s
52
ms