TEST #1808 RESULTS
11/16/2025 - 9:46 AM
ACCELERATOR
MODEL
20.2
tokens/s
generation
4.30
sec
time to first token
262
tokens/s
prompt
107
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen2.5 14B Instruct - Q4_K - Medium
SYSTEM
CPU
Apple M4 Max 10P+4E
RAM
36GB
OS
Darwin
Kernel Release
25.2.0
Architecture
arm64
Version
Cosmopolitan 3.9.7 MODE=aarch64; Darwin Kernel Version 25.2.0: Sat Nov 1 18:07:34 PDT 2025; root:xnu-12377.60.50.0.2~95/RELEASE_ARM64_T6041
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
332
tokens/s
28.5
tokens/s
3.12
sec
pp4096+tg256
310
tokens/s
20.7
tokens/s
13.24
sec
pp2048+tg256
333
tokens/s
25.1
tokens/s
6.20
sec
pp2048+tg768
335
tokens/s
24.7
tokens/s
6.16
sec
pp1024+tg1024
345
tokens/s
27.7
tokens/s
3.00
sec
pp1280+tg3072
342
tokens/s
12.6
tokens/s
3.77
sec
pp384+tg1152
166
tokens/s
14.0
tokens/s
2.36
sec
pp64+tg1024
145
tokens/s
14.5
tokens/s
491
ms
pp16+tg1536
49
tokens/s
14.3
tokens/s
372
ms
