TEST #2246 RESULTS
01/12/2026 - 11:35 AM
ACCELERATOR
MODEL
134
tokens/s
generation
245
ms
time to first token
5936
tokens/s
prompt
1480
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
QEMU Virtual CPU version 2.5+
RAM
7.8GB
OS
Linux
Kernel Release
6.8.0-90-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #91-Ubuntu SMP PREEMPT_DYNAMIC Tue Nov 18 14:14:30 UTC 2025
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
7240
tokens/s
128
tokens/s
149
ms
pp4096+tg256
4526
tokens/s
109
tokens/s
914
ms
pp2048+tg256
5518
tokens/s
128
tokens/s
380
ms
pp2048+tg768
6147
tokens/s
123
tokens/s
341
ms
pp1024+tg1024
9315
tokens/s
125
tokens/s
125
ms
pp1280+tg3072
6727
tokens/s
117
tokens/s
196
ms
pp384+tg1152
7825
tokens/s
134
tokens/s
57
ms
pp64+tg1024
5042
tokens/s
135
tokens/s
20
ms
pp16+tg1536
1087
tokens/s
204
tokens/s
22
ms