TEST #1328 RESULTS
08/07/2025 - 7:35 AM
ACCELERATOR
MODEL
62.5
tokens/s
generation
897
ms
time to first token
1475
tokens/s
prompt
468
LocalScore
HOW YOU STACK UP
Explore All ResultsDeepSeek R1 Distill Qwen 1.5B - 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
1695
tokens/s
69.4
tokens/s
619
ms
pp4096+tg256
1358
tokens/s
43.8
tokens/s
3.04
sec
pp2048+tg256
1566
tokens/s
59.1
tokens/s
1.32
sec
pp2048+tg768
1558
tokens/s
56.7
tokens/s
1.33
sec
pp1024+tg1024
1680
tokens/s
64.1
tokens/s
624
ms
pp1280+tg3072
1629
tokens/s
52.6
tokens/s
801
ms
pp384+tg1152
1725
tokens/s
69.9
tokens/s
236
ms
pp64+tg1024
1365
tokens/s
74.6
tokens/s
59
ms
pp16+tg1536
700
tokens/s
72.0
tokens/s
35
ms