TEST #2944 RESULTS
03/02/2026 - 5:26 AM
ACCELERATOR
MODEL
153
tokens/s
generation
207
ms
time to first token
7578
tokens/s
prompt
1777
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
RAM
121.7GB
OS
Linux
Kernel Release
6.17.0-1008-nvidia
Architecture
aarch64
Version
Cosmopolitan 3.9.7 MODE=aarch64; #8-Ubuntu SMP PREEMPT_DYNAMIC Wed Jan 21 17:56:56 UTC 2026
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
9229
tokens/s
155
tokens/s
119
ms
pp4096+tg256
4884
tokens/s
133
tokens/s
847
ms
pp2048+tg256
7319
tokens/s
148
tokens/s
286
ms
pp2048+tg768
7628
tokens/s
146
tokens/s
275
ms
pp1024+tg1024
8786
tokens/s
158
tokens/s
123
ms
pp1280+tg3072
9017
tokens/s
143
tokens/s
148
ms
pp384+tg1152
12970
tokens/s
165
tokens/s
35
ms
pp64+tg1024
6387
tokens/s
168
tokens/s
16
ms
pp16+tg1536
1979
tokens/s
165
tokens/s
14
ms