TEST #3651 RESULTS
05/29/2026 - 1:16 PM
ACCELERATOR
MODEL
70.0
tokens/s
generation
415
ms
time to first token
5758
tokens/s
prompt
990
LocalScore
HOW YOU STACK UP
Explore All ResultsMeta Llama 3.1 8B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD Ryzen 9 9950X3D2 16-Core Processor
RAM
60.5GB
OS
Linux
Kernel Release
7.0.2-6-pve
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #1 SMP PREEMPT_DYNAMIC PMX 7.0.2-6 (2026-05-20T08:55Z)
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
7830
tokens/s
79.8
tokens/s
143
ms
pp4096+tg256
5381
tokens/s
43.2
tokens/s
784
ms
pp2048+tg256
6583
tokens/s
59.0
tokens/s
328
ms
pp2048+tg768
6809
tokens/s
57.1
tokens/s
317
ms
pp1024+tg1024
7943
tokens/s
69.8
tokens/s
142
ms
pp1280+tg3072
7063
tokens/s
55.2
tokens/s
195
ms
pp384+tg1152
7722
tokens/s
84.2
tokens/s
60
ms
pp64+tg1024
2484
tokens/s
94.0
tokens/s
35
ms
pp16+tg1536
9
tokens/s
88.0
tokens/s
1.73
sec