TEST #2793 RESULTS
02/23/2026 - 3:42 AM
ACCELERATOR
MODEL
90.3
tokens/s
generation
283
ms
time to first token
4795
tokens/s
prompt
1152
LocalScore
HOW YOU STACK UP
Explore All ResultsDeepSeek R1 Distill Qwen 1.5B - Q4_K - Medium
SYSTEM
CPU
Intel Core i5-14450HX (alderlake)
RAM
15.7GB
OS
Windows
Kernel Release
10.0
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64
RUNTIME
Name
llamafile
Version
0.9.3
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
6076
tokens/s
90.5
tokens/s
179
ms
pp4096+tg256
4263
tokens/s
84.8
tokens/s
972
ms
pp2048+tg256
5234
tokens/s
90.0
tokens/s
404
ms
pp2048+tg768
5204
tokens/s
90.1
tokens/s
404
ms
pp1024+tg1024
5936
tokens/s
91.8
tokens/s
183
ms
pp1280+tg3072
5730
tokens/s
90.1
tokens/s
235
ms
pp384+tg1152
6836
tokens/s
91.2
tokens/s
67
ms
pp64+tg1024
2928
tokens/s
92.1
tokens/s
79
ms
pp16+tg1536
951
tokens/s
92.2
tokens/s
27
ms