TEST #3358 RESULTS

04/21/2026 - 3:58 PM

9.6

tokens/s

generation

13.62

sec

time to first token

94

tokens/s

prompt

40

LocalScore

HOW YOU STACK UP
Explore All Results

Qwen2.5 14B Instruct - Q4_K - Medium

SYSTEM
CPU
Apple M4 4P+6E
RAM
16GB
OS
Darwin
Kernel Release
24.6.0
Architecture
arm64
Version
Cosmopolitan 3.9.7 MODE=aarch64; Darwin Kernel Version 24.6.0: Mon Jan 19 22:01:41 PST 2026; root:xnu-11417.140.69.708.3~1/RELEASE_ARM64_T8132
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
108
tokens/s
10.1
tokens/s
9.61
sec
pp4096+tg256
95
tokens/s
8.1
tokens/s
43.09
sec
pp2048+tg256
100
tokens/s
9.3
tokens/s
20.63
sec
pp2048+tg768
98
tokens/s
9.1
tokens/s
21.07
sec
pp1024+tg1024
101
tokens/s
9.8
tokens/s
10.29
sec
pp1280+tg3072
100
tokens/s
8.9
tokens/s
12.88
sec
pp384+tg1152
102
tokens/s
10.1
tokens/s
3.86
sec
pp64+tg1024
100
tokens/s
10.5
tokens/s
734
ms
pp16+tg1536
46
tokens/s
10.4
tokens/s
439
ms