TEST #815 RESULTS

05/04/2025 - 10:29 AM

17.1

tokens/s

generation

6.85

sec

time to first token

180

tokens/s

prompt

77

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
24.4.0
Architecture
arm64
Version
Cosmopolitan 3.9.7 MODE=aarch64; Darwin Kernel Version 24.4.0: Fri Apr 11 18:32:50 PDT 2025; root:xnu-11417.101.15~117/RELEASE_ARM64_T6041
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
217
tokens/s
19.5
tokens/s
4.76
sec
pp4096+tg256
195
tokens/s
13.5
tokens/s
21.13
sec
pp2048+tg256
197
tokens/s
16.6
tokens/s
10.46
sec
pp2048+tg768
195
tokens/s
16.2
tokens/s
10.57
sec
pp1024+tg1024
209
tokens/s
17.8
tokens/s
4.95
sec
pp1280+tg3072
189
tokens/s
14.9
tokens/s
6.85
sec
pp384+tg1152
174
tokens/s
18.4
tokens/s
2.25
sec
pp64+tg1024
172
tokens/s
19.1
tokens/s
419
ms
pp16+tg1536
76
tokens/s
18.0
tokens/s
257
ms