TEST #155 RESULTS
03/28/2025 - 10:58 PM
ACCELERATOR
MODEL
102
tokens/s
generation
73
ms
time to first token
18337
tokens/s
prompt
2953
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD EPYC 9554 64-Core Processor (znver4)
RAM
377.4GB
OS
Linux
Kernel Release
6.8.0-52-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #53~22.04.1-Ubuntu SMP PREEMPT_DYNAMIC Wed Jan 15 19:18:46 UTC 2
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
25358
tokens/s
123
tokens/s
49
ms
pp4096+tg256
20327
tokens/s
98.6
tokens/s
212
ms
pp2048+tg256
22811
tokens/s
107
tokens/s
99
ms
pp2048+tg768
22817
tokens/s
94.0
tokens/s
99
ms
pp1024+tg1024
24615
tokens/s
82.2
tokens/s
54
ms
pp1280+tg3072
22658
tokens/s
103
tokens/s
65
ms
pp384+tg1152
21689
tokens/s
92.6
tokens/s
26
ms
pp64+tg1024
3586
tokens/s
97.3
tokens/s
29
ms
pp16+tg1536
1172
tokens/s
120
tokens/s
21
ms