TEST #1594 RESULTS

10/06/2025 - 5:20 PM

1564

tokens/s

generation

120

ms

time to first token

9787

tokens/s

prompt

5027

LocalScore

HOW YOU STACK UP
Explore All Results

Qwen2.5 14B Instruct - Q4_K - Medium

SYSTEM
CPU
Apple M3 4P+4E
RAM
16GB
OS
Darwin
Kernel Release
24.5.0
Architecture
arm64
Version
Cosmopolitan 3.9.7 MODE=aarch64; Darwin Kernel Version 24.5.0: Tue Apr 22 19:54:33 PDT 2025; root:xnu-11417.121.6~2/RELEASE_ARM64_T8122
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
8674
tokens/s
1658
tokens/s
119
ms
pp4096+tg256
10259
tokens/s
1673
tokens/s
400
ms
pp2048+tg256
11583
tokens/s
1842
tokens/s
177
ms
pp2048+tg768
15740
tokens/s
1200
tokens/s
131
ms
pp1024+tg1024
14314
tokens/s
1782
tokens/s
72
ms
pp1280+tg3072
17974
tokens/s
1461
tokens/s
72
ms
pp384+tg1152
6638
tokens/s
1100
tokens/s
59
ms
pp64+tg1024
2189
tokens/s
1308
tokens/s
32
ms
pp16+tg1536
707
tokens/s
2049
tokens/s
23
ms