TEST #348 RESULTS
04/06/2025 - 3:20 AM
ACCELERATOR
MODEL
106
tokens/s
generation
162
ms
time to first token
8549
tokens/s
prompt
1777
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD Ryzen 7 7800X3D 8-Core Processor (znver4)
RAM
31GB
OS
Linux
Kernel Release
6.13.8-201.nobara.fc41.x86_64
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #1 SMP PREEMPT_DYNAMIC Tue Mar 25 08:23:44 UTC 2025
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
11416
tokens/s
122
tokens/s
98
ms
pp4096+tg256
7121
tokens/s
83.7
tokens/s
588
ms
pp2048+tg256
9437
tokens/s
100
tokens/s
228
ms
pp2048+tg768
9521
tokens/s
96.8
tokens/s
225
ms
pp1024+tg1024
10792
tokens/s
106
tokens/s
104
ms
pp1280+tg3072
10348
tokens/s
91.4
tokens/s
133
ms
pp384+tg1152
12240
tokens/s
118
tokens/s
40
ms
pp64+tg1024
4743
tokens/s
120
tokens/s
23
ms
pp16+tg1536
1319
tokens/s
118
tokens/s
20
ms