TEST #3258 RESULTS
04/08/2026 - 10:14 PM
ACCELERATOR
MODEL
91.0
tokens/s
generation
400
ms
time to first token
3512
tokens/s
prompt
928
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen3 1.7B - Q4_K - Medium
SYSTEM
CPU
12th Gen Intel Core i7-12650H (alderlake)
RAM
15.3GB
OS
Linux
Kernel Release
6.17.0-20-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #20~24.04.1-Ubuntu SMP PREEMPT_DYNAMIC Thu Mar 19 01:28:37 UTC 2
RUNTIME
Name
llamafile
Version
0.9.3
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
4272
tokens/s
99.9
tokens/s
250
ms
pp4096+tg256
2823
tokens/s
76.9
tokens/s
1.46
sec
pp2048+tg256
3596
tokens/s
88.6
tokens/s
581
ms
pp2048+tg768
3564
tokens/s
85.9
tokens/s
589
ms
pp1024+tg1024
4202
tokens/s
93.1
tokens/s
254
ms
pp1280+tg3072
4170
tokens/s
82.8
tokens/s
317
ms
pp384+tg1152
5757
tokens/s
96.3
tokens/s
77
ms
pp64+tg1024
2403
tokens/s
99.0
tokens/s
36
ms
pp16+tg1536
825
tokens/s
96.6
tokens/s
29
ms