TEST #2253 RESULTS
01/12/2026 - 11:46 AM
ACCELERATOR
MODEL
152
tokens/s
generation
193
ms
time to first token
6752
tokens/s
prompt
1748
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
10887
tokens/s
272
tokens/s
98
ms
pp4096+tg256
6644
tokens/s
221
tokens/s
621
ms
pp2048+tg256
9095
tokens/s
120
tokens/s
229
ms
pp2048+tg768
6056
tokens/s
119
tokens/s
347
ms
pp1024+tg1024
7269
tokens/s
127
tokens/s
149
ms
pp1280+tg3072
6900
tokens/s
118
tokens/s
191
ms
pp384+tg1152
8171
tokens/s
125
tokens/s
55
ms
pp64+tg1024
4784
tokens/s
136
tokens/s
21
ms
pp16+tg1536
962
tokens/s
135
tokens/s
24
ms