TEST #1610 RESULTS
10/07/2025 - 9:46 PM
ACCELERATOR
MODEL
7.5
tokens/s
generation
7.90
sec
time to first token
164
tokens/s
prompt
54
LocalScore
HOW YOU STACK UP
Explore All ResultsDeepSeek R1 Distill Qwen 1.5B - IQ4_XS - 4.25 bpw
SYSTEM
CPU
Intel Core i5-10400 CPU @ 2.90GHz (skylake)
RAM
31.3GB
OS
Linux
Kernel Release
6.8.0-84-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #84-Ubuntu SMP PREEMPT_DYNAMIC Fri Sep 5 22:36:38 UTC 2025
RUNTIME
Name
llamafile
Version
0.9.3
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
182
tokens/s
8.2
tokens/s
5.77
sec
pp4096+tg256
162
tokens/s
5.6
tokens/s
25.41
sec
pp2048+tg256
174
tokens/s
7.1
tokens/s
11.90
sec
pp2048+tg768
173
tokens/s
6.8
tokens/s
11.99
sec
pp1024+tg1024
182
tokens/s
7.7
tokens/s
5.77
sec
pp1280+tg3072
179
tokens/s
6.5
tokens/s
7.27
sec
pp384+tg1152
182
tokens/s
8.4
tokens/s
2.23
sec
pp64+tg1024
155
tokens/s
9.0
tokens/s
517
ms
pp16+tg1536
86
tokens/s
8.5
tokens/s
290
ms