TEST #3456 RESULTS
05/06/2026 - 9:11 PM
ACCELERATOR
MODEL
216
tokens/s
generation
1.20
sec
time to first token
10380
tokens/s
prompt
1231
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
Intel Core Ultra 5 235 (arrowlake-s)
RAM
62.2GB
OS
Linux
Kernel Release
6.17.0-23-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #23~24.04.1-Ubuntu SMP PREEMPT_DYNAMIC Tue Apr 14 16:11:48 UTC 2
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
13143
tokens/s
243
tokens/s
82
ms
pp4096+tg256
7423
tokens/s
144
tokens/s
559
ms
pp2048+tg256
10337
tokens/s
195
tokens/s
203
ms
pp2048+tg768
10336
tokens/s
186
tokens/s
203
ms
pp1024+tg1024
13097
tokens/s
219
tokens/s
82
ms
pp1280+tg3072
12167
tokens/s
176
tokens/s
110
ms
pp384+tg1152
17091
tokens/s
246
tokens/s
26
ms
pp64+tg1024
9821
tokens/s
273
tokens/s
10
ms
pp16+tg1536
2
tokens/s
260
tokens/s
9.54
sec