TEST #263 RESULTS

04/05/2025 - 1:27 AM

12.0

tokens/s

generation

10.75

sec

time to first token

117

tokens/s

prompt

51

LocalScore

HOW YOU STACK UP
Explore All Results

Qwen2.5 14B Instruct - Q4_K - Medium

SYSTEM
CPU
Apple M3 Pro 5P+6E
RAM
18GB
OS
Darwin
Kernel Release
23.6.0
Architecture
arm64
Version
Cosmopolitan 3.9.7 MODE=aarch64; Darwin Kernel Version 23.6.0: Thu Dec 19 20:47:53 PST 2024; root:xnu-10063.141.1.703.2~1/RELEASE_ARM64_T6030
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
133
tokens/s
12.8
tokens/s
7.79
sec
pp4096+tg256
118
tokens/s
9.9
tokens/s
34.69
sec
pp2048+tg256
128
tokens/s
11.5
tokens/s
16.04
sec
pp2048+tg768
127
tokens/s
11.3
tokens/s
16.16
sec
pp1024+tg1024
131
tokens/s
11.9
tokens/s
7.87
sec
pp1280+tg3072
128
tokens/s
10.8
tokens/s
10.09
sec
pp384+tg1152
128
tokens/s
12.9
tokens/s
3.07
sec
pp64+tg1024
114
tokens/s
13.3
tokens/s
634
ms
pp16+tg1536
43
tokens/s
13.1
tokens/s
443
ms