TEST #3343 RESULTS

04/18/2026 - 6:49 AM

18.0

tokens/s

generation

6.72

sec

time to first token

187

tokens/s

prompt

79

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
25.4.0
Architecture
arm64
Version
Cosmopolitan 3.9.7 MODE=aarch64; Darwin Kernel Version 25.4.0: Thu Mar 19 19:33:25 PDT 2026; root:xnu-12377.101.15~1/RELEASE_ARM64_T6041
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
210
tokens/s
19.5
tokens/s
4.93
sec
pp4096+tg256
194
tokens/s
13.6
tokens/s
21.18
sec
pp2048+tg256
204
tokens/s
16.9
tokens/s
10.09
sec
pp2048+tg768
198
tokens/s
16.5
tokens/s
10.40
sec
pp1024+tg1024
202
tokens/s
18.3
tokens/s
5.12
sec
pp1280+tg3072
205
tokens/s
15.9
tokens/s
6.29
sec
pp384+tg1152
214
tokens/s
19.8
tokens/s
1.84
sec
pp64+tg1024
185
tokens/s
20.8
tokens/s
390
ms
pp16+tg1536
74
tokens/s
20.3
tokens/s
259
ms