TEST #1576 RESULTS
10/02/2025 - 2:16 AM
ACCELERATOR
MODEL
30.9
tokens/s
generation
6.07
sec
time to first token
241
tokens/s
prompt
107
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD Ryzen 7 5800X 8-Core Processor (znver3)
RAM
62.7GB
OS
Linux
Kernel Release
6.8.0-83-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #83~22.04.1-Ubuntu SMP PREEMPT_DYNAMIC Tue Sep 9 18:19:47 UTC 2
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
248
tokens/s
36.3
tokens/s
4.16
sec
pp4096+tg256
196
tokens/s
26.9
tokens/s
20.90
sec
pp2048+tg256
227
tokens/s
29.5
tokens/s
9.04
sec
pp2048+tg768
225
tokens/s
29.1
tokens/s
9.15
sec
pp1024+tg1024
247
tokens/s
31.2
tokens/s
4.18
sec
pp1280+tg3072
243
tokens/s
28.6
tokens/s
5.30
sec
pp384+tg1152
260
tokens/s
32.4
tokens/s
1.50
sec
pp64+tg1024
273
tokens/s
32.0
tokens/s
271
ms
pp16+tg1536
251
tokens/s
32.1
tokens/s
90
ms