TEST #1618 RESULTS
10/08/2025 - 4:46 AM
ACCELERATOR
MODEL
14.8
tokens/s
generation
4.44
sec
time to first token
317
tokens/s
prompt
102
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen3 Coder 0.6B 0.9B 7 1bR5 Nobs F16 - F16
SYSTEM
CPU
Intel Core i5-10400 CPU @ 2.90GHz (skylake)
RAM
31.3GB
OS
Linux
Kernel Release
6.8.0-85-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #85-Ubuntu SMP PREEMPT_DYNAMIC Thu Sep 18 15:26:59 UTC 2025
RUNTIME
Name
llamafile
Version
0.9.3
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
358
tokens/s
18.1
tokens/s
2.92
sec
pp4096+tg256
265
tokens/s
5.4
tokens/s
15.62
sec
pp2048+tg256
316
tokens/s
9.6
tokens/s
6.57
sec
pp2048+tg768
316
tokens/s
8.8
tokens/s
6.57
sec
pp1024+tg1024
353
tokens/s
13.2
tokens/s
2.96
sec
pp1280+tg3072
339
tokens/s
7.7
tokens/s
3.84
sec
pp384+tg1152
334
tokens/s
19.3
tokens/s
1.18
sec
pp64+tg1024
331
tokens/s
28.2
tokens/s
208
ms
pp16+tg1536
238
tokens/s
22.7
tokens/s
79
ms