TEST #2268 RESULTS

01/12/2026 - 11:27 PM

18.3

tokens/s

generation

6.38

sec

time to first token

197

tokens/s

prompt

83

LocalScore

HOW YOU STACK UP
Explore All Results

Qwen2.5 14B Instruct - Q4_K - Medium

SYSTEM
CPU
Apple M4 Pro 10P+4E
RAM
48GB
OS
Darwin
Kernel Release
25.2.0
Architecture
arm64
Version
Cosmopolitan 3.9.7 MODE=aarch64; Darwin Kernel Version 25.2.0: Tue Nov 18 21:09:56 PST 2025; root:xnu-12377.61.12~1/RELEASE_ARM64_T6041
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
221
tokens/s
19.9
tokens/s
4.69
sec
pp4096+tg256
203
tokens/s
13.9
tokens/s
20.29
sec
pp2048+tg256
214
tokens/s
17.2
tokens/s
9.61
sec
pp2048+tg768
215
tokens/s
16.7
tokens/s
9.60
sec
pp1024+tg1024
220
tokens/s
18.7
tokens/s
4.71
sec
pp1280+tg3072
214
tokens/s
16.1
tokens/s
6.04
sec
pp384+tg1152
216
tokens/s
20.5
tokens/s
1.82
sec
pp64+tg1024
191
tokens/s
21.1
tokens/s
379
ms
pp16+tg1536
77
tokens/s
20.5
tokens/s
252
ms