TEST #1658 RESULTS

10/16/2025 - 1:21 PM

16.7

tokens/s

generation

8.32

sec

time to first token

153

tokens/s

prompt

67

LocalScore

HOW YOU STACK UP
Explore All Results

Qwen2.5 14B Instruct - Q4_K - Medium

SYSTEM
CPU
Apple M4 Pro 8P+4E
RAM
24GB
OS
Darwin
Kernel Release
25.0.0
Architecture
arm64
Version
Cosmopolitan 3.9.7 MODE=aarch64; Darwin Kernel Version 25.0.0: Mon Aug 25 21:17:54 PDT 2025; root:xnu-12377.1.9~3/RELEASE_ARM64_T6041
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
169
tokens/s
17.9
tokens/s
6.10
sec
pp4096+tg256
156
tokens/s
12.8
tokens/s
26.37
sec
pp2048+tg256
161
tokens/s
15.8
tokens/s
12.82
sec
pp2048+tg768
160
tokens/s
15.5
tokens/s
12.86
sec
pp1024+tg1024
171
tokens/s
17.1
tokens/s
6.04
sec
pp1280+tg3072
169
tokens/s
14.9
tokens/s
7.62
sec
pp384+tg1152
173
tokens/s
18.3
tokens/s
2.27
sec
pp64+tg1024
152
tokens/s
19.1
tokens/s
470
ms
pp16+tg1536
65
tokens/s
18.6
tokens/s
294
ms