TEST #3891 RESULTS
07/12/2026 - 4:52 AM
ACCELERATOR
MODEL
34.2
tokens/s
generation
1.85
sec
time to first token
765
tokens/s
prompt
242
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD Ryzen 5 2600 Six-Core Processor
RAM
7.7GB
OS
Linux
Kernel Release
7.0.12-arch1-1
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #1 SMP PREEMPT_DYNAMIC Wed, 10 Jun 2026 08:58:02 +0000
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
863
tokens/s
41.4
tokens/s
1.21
sec
pp4096+tg256
624
tokens/s
13.5
tokens/s
6.63
sec
pp2048+tg256
764
tokens/s
23.9
tokens/s
2.72
sec
pp2048+tg768
761
tokens/s
21.7
tokens/s
2.73
sec
pp1024+tg1024
851
tokens/s
31.5
tokens/s
1.23
sec
pp1280+tg3072
828
tokens/s
19.1
tokens/s
1.57
sec
pp384+tg1152
922
tokens/s
44.4
tokens/s
430
ms
pp64+tg1024
925
tokens/s
61.4
tokens/s
77
ms
pp16+tg1536
349
tokens/s
51.0
tokens/s
53
ms