TEST #1689 RESULTS
10/19/2025 - 8:45 PM
ACCELERATOR
MODEL
25.5
tokens/s
generation
4.03
sec
time to first token
302
tokens/s
prompt
124
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen2.5 14B Instruct - Q4_K - Medium
SYSTEM
CPU
Apple M3 Max 12P+4E
RAM
128GB
OS
Darwin
Kernel Release
25.0.0
Architecture
arm64
Version
Cosmopolitan 3.9.7 MODE=aarch64; Darwin Kernel Version 25.0.0: Wed Sep 17 21:38:50 PDT 2025; root:xnu-12377.1.9~141/RELEASE_ARM64_T6031
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
371
tokens/s
28.0
tokens/s
2.80
sec
pp4096+tg256
336
tokens/s
19.0
tokens/s
12.23
sec
pp2048+tg256
345
tokens/s
24.0
tokens/s
5.98
sec
pp2048+tg768
324
tokens/s
23.4
tokens/s
6.36
sec
pp1024+tg1024
325
tokens/s
26.2
tokens/s
3.19
sec
pp1280+tg3072
317
tokens/s
22.2
tokens/s
4.07
sec
pp384+tg1152
347
tokens/s
28.5
tokens/s
1.14
sec
pp64+tg1024
272
tokens/s
29.7
tokens/s
266
ms
pp16+tg1536
83
tokens/s
28.4
tokens/s
223
ms
