TEST #1029 RESULTS
06/11/2025 - 4:39 AM
ACCELERATOR
MODEL
146
tokens/s
generation
317
ms
time to first token
4075
tokens/s
prompt
1233
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD FX(tm)-8320 Eight-Core Processor (bdver2)
RAM
7.5GB
OS
Linux
Kernel Release
5.14.0-570.19.1.el9_6.x86_64
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #1 SMP PREEMPT_DYNAMIC Sat Jun 7 09:41:17 UTC 2025
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
5019
tokens/s
141
tokens/s
211
ms
pp4096+tg256
3755
tokens/s
102
tokens/s
1.10
sec
pp2048+tg256
4533
tokens/s
135
tokens/s
459
ms
pp2048+tg768
4545
tokens/s
131
tokens/s
458
ms
pp1024+tg1024
4994
tokens/s
152
tokens/s
211
ms
pp1280+tg3072
4624
tokens/s
124
tokens/s
283
ms
pp384+tg1152
5248
tokens/s
168
tokens/s
79
ms
pp64+tg1024
2973
tokens/s
182
tokens/s
27
ms
pp16+tg1536
988
tokens/s
175
tokens/s
21
ms