TEST #2989 RESULTS
03/06/2026 - 9:08 AM
ACCELERATOR
MODEL
4.8
tokens/s
generation
30.20
sec
time to first token
41
tokens/s
prompt
19
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen2.5 14B Instruct - Q4_K - Medium
SYSTEM
CPU
Apple M1 4P+4E
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 21:58:37 PST 2026; root:xnu-11417.140.69.708.3~1/RELEASE_ARM64_T8103
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
51
tokens/s
5.7
tokens/s
20.18
sec
pp4096+tg256
46
tokens/s
4.1
tokens/s
88.89
sec
pp2048+tg256
46
tokens/s
4.9
tokens/s
44.67
sec
pp2048+tg768
45
tokens/s
4.5
tokens/s
45.82
sec
pp1024+tg1024
39
tokens/s
4.7
tokens/s
26.45
sec
pp1280+tg3072
39
tokens/s
4.1
tokens/s
33.24
sec
pp384+tg1152
40
tokens/s
4.9
tokens/s
9.81
sec
pp64+tg1024
41
tokens/s
5.3
tokens/s
1.74
sec
pp16+tg1536
19
tokens/s
5.1
tokens/s
1.01
sec