TEST #3361 RESULTS
04/21/2026 - 11:19 PM
ACCELERATOR
MODEL
16.7
tokens/s
generation
8.24
sec
time to first token
154
tokens/s
prompt
68
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen2.5 14B Instruct - Q4_K - Medium
SYSTEM
CPU
Apple M4 Pro 8P+4E
RAM
24GB
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
174
tokens/s
17.9
tokens/s
5.95
sec
pp4096+tg256
162
tokens/s
13.0
tokens/s
25.30
sec
pp2048+tg256
160
tokens/s
15.8
tokens/s
12.86
sec
pp2048+tg768
156
tokens/s
15.4
tokens/s
13.15
sec
pp1024+tg1024
166
tokens/s
17.0
tokens/s
6.21
sec
pp1280+tg3072
168
tokens/s
14.9
tokens/s
7.67
sec
pp384+tg1152
172
tokens/s
18.3
tokens/s
2.29
sec
pp64+tg1024
161
tokens/s
19.2
tokens/s
446
ms
pp16+tg1536
70
tokens/s
18.7
tokens/s
276
ms
