TEST #141 RESULTS
03/28/2025 - 10:19 PM
ACCELERATOR
MODEL
396
tokens/s
generation
65
ms
time to first token
25164
tokens/s
prompt
5354
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD EPYC 7B13 64-Core Processor (znver3)
RAM
2003.9GB
OS
Linux
Kernel Release
5.4.0-174-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #193-Ubuntu SMP Thu Mar 7 14:29:28 UTC 2024
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
34657
tokens/s
398
tokens/s
32
ms
pp4096+tg256
14186
tokens/s
348
tokens/s
292
ms
pp2048+tg256
29093
tokens/s
385
tokens/s
73
ms
pp2048+tg768
26893
tokens/s
384
tokens/s
79
ms
pp1024+tg1024
36327
tokens/s
396
tokens/s
31
ms
pp1280+tg3072
34800
tokens/s
375
tokens/s
39
ms
pp384+tg1152
37207
tokens/s
421
tokens/s
13
ms
pp64+tg1024
12316
tokens/s
434
tokens/s
7
ms
pp16+tg1536
998
tokens/s
421
tokens/s
18
ms