TEST #2892 RESULTS
02/24/2026 - 8:37 AM
ACCELERATOR
MODEL
66.3
tokens/s
generation
1.43
sec
time to first token
904
tokens/s
prompt
347
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
Apple M4 4P+6E
RAM
16GB
OS
Darwin
Kernel Release
25.2.0
Architecture
arm64
Version
Cosmopolitan 3.9.7 MODE=aarch64; Darwin Kernel Version 25.2.0: Tue Nov 18 21:08:48 PST 2025; root:xnu-12377.61.12~1/RELEASE_ARM64_T8132
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
1048
tokens/s
74.2
tokens/s
991
ms
pp4096+tg256
841
tokens/s
46.5
tokens/s
4.89
sec
pp2048+tg256
981
tokens/s
61.1
tokens/s
2.10
sec
pp2048+tg768
981
tokens/s
58.8
tokens/s
2.10
sec
pp1024+tg1024
1047
tokens/s
67.8
tokens/s
992
ms
pp1280+tg3072
1032
tokens/s
55.5
tokens/s
1.25
sec
pp384+tg1152
1047
tokens/s
75.0
tokens/s
379
ms
pp64+tg1024
828
tokens/s
80.5
tokens/s
89
ms
pp16+tg1536
330
tokens/s
77.4
tokens/s
60
ms