TEST #2520 RESULTS
02/03/2026 - 7:22 PM
ACCELERATOR
MODEL
118
tokens/s
generation
96
ms
time to first token
13485
tokens/s
prompt
2548
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD Ryzen 7 9800X3D 8-Core Processor
RAM
60.4GB
OS
Linux
Kernel Release
6.18.7-1-default
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #1 SMP PREEMPT_DYNAMIC Fri Jan 23 12:13:24 UTC 2026 (14faf12)
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
18213
tokens/s
145
tokens/s
63
ms
pp4096+tg256
13782
tokens/s
95.0
tokens/s
308
ms
pp2048+tg256
16091
tokens/s
117
tokens/s
136
ms
pp2048+tg768
16088
tokens/s
102
tokens/s
136
ms
pp1024+tg1024
18215
tokens/s
122
tokens/s
63
ms
pp1280+tg3072
16711
tokens/s
101
tokens/s
85
ms
pp384+tg1152
16960
tokens/s
124
tokens/s
31
ms
pp64+tg1024
4145
tokens/s
128
tokens/s
22
ms
pp16+tg1536
1156
tokens/s
127
tokens/s
21
ms