TEST #1325 RESULTS
08/07/2025 - 7:12 AM
ACCELERATOR
MODEL
19.1
tokens/s
generation
3.53
sec
time to first token
365
tokens/s
prompt
125
LocalScore
HOW YOU STACK UP
Explore All ResultsDeepSeek R1 Distill Qwen 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
411
tokens/s
20.8
tokens/s
2.54
sec
pp4096+tg256
360
tokens/s
14.9
tokens/s
11.45
sec
pp2048+tg256
392
tokens/s
18.3
tokens/s
5.28
sec
pp2048+tg768
391
tokens/s
17.8
tokens/s
5.30
sec
pp1024+tg1024
408
tokens/s
19.6
tokens/s
2.56
sec
pp1280+tg3072
400
tokens/s
16.9
tokens/s
3.25
sec
pp384+tg1152
398
tokens/s
20.9
tokens/s
1.01
sec
pp64+tg1024
391
tokens/s
21.5
tokens/s
207
ms
pp16+tg1536
130
tokens/s
21.2
tokens/s
166
ms