TEST #976 RESULTS
06/02/2025 - 5:46 PM
ACCELERATOR
MODEL
105
tokens/s
generation
431
ms
time to first token
3091
tokens/s
prompt
911
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
11th Gen Intel Core i9-11950H @ 2.60GHz (tigerlake)
RAM
62.5GB
OS
Linux
Kernel Release
6.11.0-26-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #26~24.04.1-Ubuntu SMP PREEMPT_DYNAMIC Thu Apr 17 19:20:47 UTC 2
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
4034
tokens/s
130
tokens/s
261
ms
pp4096+tg256
2625
tokens/s
97.5
tokens/s
1.57
sec
pp2048+tg256
3434
tokens/s
114
tokens/s
605
ms
pp2048+tg768
3430
tokens/s
110
tokens/s
606
ms
pp1024+tg1024
3985
tokens/s
106
tokens/s
265
ms
pp1280+tg3072
3425
tokens/s
82.8
tokens/s
383
ms
pp384+tg1152
3505
tokens/s
100
tokens/s
119
ms
pp64+tg1024
2728
tokens/s
105
tokens/s
32
ms
pp16+tg1536
656
tokens/s
102
tokens/s
33
ms