TEST #656 RESULTS
04/09/2025 - 11:59 PM
ACCELERATOR
MODEL
340
tokens/s
generation
95
ms
time to first token
13805
tokens/s
prompt
3676
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD Ryzen 9 3900X 12-Core Processor (znver2)
RAM
31.2GB
OS
Linux
Kernel Release
6.11.0-21-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #21~24.04.1-Ubuntu SMP PREEMPT_DYNAMIC Mon Feb 24 16:52:15 UTC 2
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
17196
tokens/s
331
tokens/s
62
ms
pp4096+tg256
12293
tokens/s
293
tokens/s
337
ms
pp2048+tg256
15809
tokens/s
339
tokens/s
133
ms
pp2048+tg768
15911
tokens/s
331
tokens/s
132
ms
pp1024+tg1024
18462
tokens/s
350
tokens/s
58
ms
pp1280+tg3072
16933
tokens/s
321
tokens/s
78
ms
pp384+tg1152
17971
tokens/s
359
tokens/s
24
ms
pp64+tg1024
8531
tokens/s
372
tokens/s
10
ms
pp16+tg1536
1138
tokens/s
366
tokens/s
17
ms