TEST #15 RESULTS
03/24/2025 - 6:27 PM
ACCELERATOR
MODEL
130
tokens/s
generation
179
ms
time to first token
11035
tokens/s
prompt
2001
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD Ryzen 7 5700X 8-Core Processor (znver3)
RAM
62.72GB
OS
Linux
Kernel Release
6.8.0-40-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #40~22.04.3-Ubuntu SMP PREEMPT_DYNAMIC Tue Jul 30 17:30:19 UTC 2
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
13521
tokens/s
141
tokens/s
83
ms
pp4096+tg256
5091
tokens/s
162
tokens/s
811
ms
pp2048+tg256
8867
tokens/s
83.4
tokens/s
242
ms
pp2048+tg768
8884
tokens/s
76.5
tokens/s
242
ms
pp1024+tg1024
13898
tokens/s
109
tokens/s
81
ms
pp1280+tg3072
12471
tokens/s
74.7
tokens/s
111
ms
pp384+tg1152
20087
tokens/s
150
tokens/s
23
ms
pp64+tg1024
12364
tokens/s
201
tokens/s
8
ms
pp16+tg1536
4128
tokens/s
169
tokens/s
7
ms