TEST #1320 RESULTS
08/07/2025 - 2:41 AM
ACCELERATOR
MODEL
99.5
tokens/s
generation
410
ms
time to first token
3987
tokens/s
prompt
989
LocalScore
HOW YOU STACK UP
Explore All Resultstinyllama_tinyllama-1.1b-chat-v1.0 - Q8_0
SYSTEM
CPU
13th Gen Intel Core i7-13700H (alderlake)
RAM
38.8GB
OS
Linux
Kernel Release
6.14.0-27-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #27~24.04.1-Ubuntu SMP PREEMPT_DYNAMIC Tue Jul 22 17:38:49 UTC 2
RUNTIME
Name
llamafile
Version
0.9.3
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
4504
tokens/s
109
tokens/s
237
ms
pp4096+tg256
2586
tokens/s
84.1
tokens/s
1.60
sec
pp2048+tg256
3599
tokens/s
97.7
tokens/s
580
ms
pp2048+tg768
3526
tokens/s
95.2
tokens/s
592
ms
pp1024+tg1024
4525
tokens/s
102
tokens/s
236
ms
pp1280+tg3072
3801
tokens/s
90.5
tokens/s
346
ms
pp384+tg1152
7019
tokens/s
104
tokens/s
64
ms
pp64+tg1024
4804
tokens/s
107
tokens/s
22
ms
pp16+tg1536
1519
tokens/s
105
tokens/s
19
ms