TEST #1329 RESULTS
08/07/2025 - 7:48 AM
ACCELERATOR
MODEL
51.0
tokens/s
generation
1.43
sec
time to first token
1000
tokens/s
prompt
329
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen3 1.7B - Q4_K - Medium
SYSTEM
CPU
Intel Core i5-6600K CPU @ 3.50GHz (skylake)
RAM
15.1GB
OS
Linux
Kernel Release
6.14.0-27-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #27-Ubuntu SMP PREEMPT_DYNAMIC Tue Jul 22 17:01:58 UTC 2025
RUNTIME
Name
llamafile
Version
0.9.3
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
417
tokens/s
59.3
tokens/s
2.47
sec
pp4096+tg256
908
tokens/s
32.2
tokens/s
4.54
sec
pp2048+tg256
1266
tokens/s
46.1
tokens/s
1.64
sec
pp2048+tg768
1265
tokens/s
44.0
tokens/s
1.70
sec
pp1024+tg1024
954
tokens/s
51.8
tokens/s
1.09
sec
pp1280+tg3072
1259
tokens/s
40.7
tokens/s
1.04
sec
pp384+tg1152
1253
tokens/s
58.7
tokens/s
321
ms
pp64+tg1024
1167
tokens/s
64.5
tokens/s
69
ms
pp16+tg1536
514
tokens/s
61.3
tokens/s
45
ms