TEST #2323 RESULTS
01/19/2026 - 2:31 PM
ACCELERATOR
MODEL
52.0
tokens/s
generation
10.87
sec
time to first token
124
tokens/s
prompt
84
LocalScore
HOW YOU STACK UP
Explore All ResultsMinueza 2 96M Instruct Variant 03 - Q4_0
SYSTEM
CPU
AMD A6-5200 APU with Radeon HD Graphics
RAM
3.3GB
OS
Linux
Kernel Release
6.12.11-tinycore64
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #1 SMP Sun Jan 26 16:50:13 UTC 2025
RUNTIME
Name
llamafile
Version
0.9.3
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
157
tokens/s
70.7
tokens/s
6.55
sec
pp4096+tg256
114
tokens/s
44.3
tokens/s
36.10
sec
pp2048+tg256
136
tokens/s
57.7
tokens/s
15.05
sec
pp2048+tg768
123
tokens/s
47.5
tokens/s
16.67
sec
pp1024+tg1024
124
tokens/s
53.6
tokens/s
8.27
sec
pp1280+tg3072
115
tokens/s
39.4
tokens/s
11.17
sec
pp384+tg1152
115
tokens/s
50.4
tokens/s
3.34
sec
pp64+tg1024
123
tokens/s
53.8
tokens/s
534
ms
pp16+tg1536
109
tokens/s
50.4
tokens/s
162
ms