TEST #3458 RESULTS

05/07/2026 - 1:56 AM

7.3

tokens/s

generation

19.56

sec

time to first token

61

tokens/s

prompt

28

LocalScore

HOW YOU STACK UP
Explore All Results

Qwen2.5 14B Instruct - Q4_K - Medium

SYSTEM
CPU
Apple M4 4P+6E
RAM
16GB
OS
Darwin
Kernel Release
25.4.0
Architecture
arm64
Version
Cosmopolitan 3.9.7 MODE=aarch64; Darwin Kernel Version 25.4.0: Thu Mar 19 19:31:09 PDT 2026; root:xnu-12377.101.15~1/RELEASE_ARM64_T8132
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
81
tokens/s
9.3
tokens/s
12.71
sec
pp4096+tg256
72
tokens/s
7.1
tokens/s
56.76
sec
pp2048+tg256
72
tokens/s
8.0
tokens/s
28.50
sec
pp2048+tg768
70
tokens/s
7.6
tokens/s
29.45
sec
pp1024+tg1024
67
tokens/s
7.5
tokens/s
15.47
sec
pp1280+tg3072
55
tokens/s
5.7
tokens/s
23.59
sec
pp384+tg1152
54
tokens/s
5.9
tokens/s
7.29
sec
pp64+tg1024
48
tokens/s
6.8
tokens/s
1.49
sec
pp16+tg1536
26
tokens/s
7.7
tokens/s
733
ms