TEST #3435 RESULTS
05/04/2026 - 12:20 AM
ACCELERATOR
MODEL
18.3
tokens/s
generation
3.79
sec
time to first token
432
tokens/s
prompt
128
LocalScore
HOW YOU STACK UP
Explore All ResultsDeepseek-R1-0528-Qwen3-8B - 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
422
tokens/s
23.8
tokens/s
2.47
sec
pp4096+tg256
272
tokens/s
2.7
tokens/s
15.39
sec
pp2048+tg256
397
tokens/s
17.0
tokens/s
5.21
sec
pp2048+tg768
397
tokens/s
15.8
tokens/s
5.22
sec
pp1024+tg1024
492
tokens/s
19.8
tokens/s
2.12
sec
pp1280+tg3072
480
tokens/s
10.3
tokens/s
2.71
sec
pp384+tg1152
576
tokens/s
23.7
tokens/s
703
ms
pp64+tg1024
537
tokens/s
26.3
tokens/s
152
ms
pp16+tg1536
314
tokens/s
25.2
tokens/s
83
ms