TEST #82 RESULTS
03/28/2025 - 9:16 PM
ACCELERATOR
MODEL
118
tokens/s
generation
77
ms
time to first token
17686
tokens/s
prompt
3000
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD EPYC 9354 32-Core Processor (znver4)
RAM
755.6GB
OS
Linux
Kernel Release
6.8.0-50-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #51~22.04.1-Ubuntu SMP PREEMPT_DYNAMIC Thu Nov 21 12:03:03 UTC 2
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
25359
tokens/s
124
tokens/s
48
ms
pp4096+tg256
16578
tokens/s
108
tokens/s
256
ms
pp2048+tg256
21509
tokens/s
118
tokens/s
104
ms
pp2048+tg768
21463
tokens/s
115
tokens/s
104
ms
pp1024+tg1024
25234
tokens/s
119
tokens/s
49
ms
pp1280+tg3072
20660
tokens/s
114
tokens/s
70
ms
pp384+tg1152
21653
tokens/s
121
tokens/s
26
ms
pp64+tg1024
5236
tokens/s
121
tokens/s
19
ms
pp16+tg1536
1481
tokens/s
122
tokens/s
18
ms