TEST #570 RESULTS
04/08/2025 - 9:12 AM
ACCELERATOR
MODEL
250
tokens/s
generation
141
ms
time to first token
9356
tokens/s
prompt
2550
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
QEMU Virtual CPU version 2.5+
RAM
295GB
OS
Linux
Kernel Release
6.8.0-57-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #59-Ubuntu SMP PREEMPT_DYNAMIC Sat Mar 15 17:40:59 UTC 2025
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
11119
tokens/s
268
tokens/s
96
ms
pp4096+tg256
8195
tokens/s
197
tokens/s
505
ms
pp2048+tg256
10590
tokens/s
244
tokens/s
198
ms
pp2048+tg768
10587
tokens/s
234
tokens/s
198
ms
pp1024+tg1024
12078
tokens/s
262
tokens/s
88
ms
pp1280+tg3072
11373
tokens/s
223
tokens/s
118
ms
pp384+tg1152
12605
tokens/s
266
tokens/s
34
ms
pp64+tg1024
6775
tokens/s
271
tokens/s
13
ms
pp16+tg1536
884
tokens/s
289
tokens/s
21
ms