TEST #1331 RESULTS
08/07/2025 - 8:01 AM
ACCELERATOR
MODEL
86.5
tokens/s
generation
787
ms
time to first token
1782
tokens/s
prompt
581
LocalScore
HOW YOU STACK UP
Explore All ResultsTinyLlama - Q4_0
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
2097
tokens/s
96.4
tokens/s
499
ms
pp4096+tg256
1428
tokens/s
49.6
tokens/s
2.89
sec
pp2048+tg256
1815
tokens/s
75.4
tokens/s
1.14
sec
pp2048+tg768
1808
tokens/s
70.5
tokens/s
1.15
sec
pp1024+tg1024
2080
tokens/s
88.3
tokens/s
502
ms
pp1280+tg3072
1967
tokens/s
64.1
tokens/s
661
ms
pp384+tg1152
2269
tokens/s
104
tokens/s
177
ms
pp64+tg1024
1813
tokens/s
119
tokens/s
42
ms
pp16+tg1536
765
tokens/s
111
tokens/s
28
ms