TEST #984 RESULTS
06/03/2025 - 3:51 AM
ACCELERATOR
MODEL
60.4
tokens/s
generation
447
ms
time to first token
2851
tokens/s
prompt
728
LocalScore
HOW YOU STACK UP
Explore All ResultsDeepSeek R1 Distill Qwen 1.5B - Q4_K - Medium
SYSTEM
CPU
Intel Core i5-4590 CPU @ 3.30GHz (haswell)
RAM
31.9GB
OS
Windows
Kernel Release
10.0
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
3585
tokens/s
63.2
tokens/s
305
ms
pp4096+tg256
2795
tokens/s
63.2
tokens/s
1.48
sec
pp2048+tg256
3298
tokens/s
60.9
tokens/s
638
ms
pp2048+tg768
3275
tokens/s
56.5
tokens/s
643
ms
pp1024+tg1024
3601
tokens/s
64.1
tokens/s
299
ms
pp1280+tg3072
3455
tokens/s
60.5
tokens/s
386
ms
pp384+tg1152
3848
tokens/s
59.8
tokens/s
120
ms
pp64+tg1024
1356
tokens/s
59.6
tokens/s
97
ms
pp16+tg1536
444
tokens/s
55.7
tokens/s
51
ms