TEST #417 RESULTS
04/06/2025 - 8:03 PM
ACCELERATOR
MODEL
22.2
tokens/s
generation
3.18
sec
time to first token
447
tokens/s
prompt
146
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
Intel Xeon CPU E5-2699 v3 @ 2.30GHz (haswell)
RAM
377.8GB
OS
Linux
Kernel Release
6.12.12-1-lts
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #1 SMP PREEMPT_DYNAMIC Sat, 01 Feb 2025 18:47:29 +0000
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
355
tokens/s
27.7
tokens/s
2.91
sec
pp4096+tg256
358
tokens/s
21.1
tokens/s
11.46
sec
pp2048+tg256
499
tokens/s
20.8
tokens/s
4.13
sec
pp2048+tg768
472
tokens/s
20.6
tokens/s
4.36
sec
pp1024+tg1024
501
tokens/s
21.2
tokens/s
2.07
sec
pp1280+tg3072
458
tokens/s
21.0
tokens/s
2.82
sec
pp384+tg1152
611
tokens/s
22.5
tokens/s
654
ms
pp64+tg1024
530
tokens/s
22.6
tokens/s
147
ms
pp16+tg1536
236
tokens/s
21.9
tokens/s
95
ms