TEST #2939 RESULTS

03/01/2026 - 9:24 AM

8.5

tokens/s

generation

16.81

sec

time to first token

74

tokens/s

prompt

33

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
25.3.0
Architecture
arm64
Version
Cosmopolitan 3.9.7 MODE=aarch64; Darwin Kernel Version 25.3.0: Wed Jan 28 20:49:24 PST 2026; root:xnu-12377.81.4~5/RELEASE_ARM64_T8132
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
93
tokens/s
10.1
tokens/s
11.13
sec
pp4096+tg256
80
tokens/s
7.6
tokens/s
51.29
sec
pp2048+tg256
81
tokens/s
8.6
tokens/s
25.25
sec
pp2048+tg768
78
tokens/s
7.6
tokens/s
26.31
sec
pp1024+tg1024
75
tokens/s
8.5
tokens/s
13.86
sec
pp1280+tg3072
78
tokens/s
7.7
tokens/s
16.63
sec
pp384+tg1152
76
tokens/s
8.8
tokens/s
5.18
sec
pp64+tg1024
70
tokens/s
9.0
tokens/s
1.02
sec
pp16+tg1536
32
tokens/s
8.7
tokens/s
606
ms