TEST #3061 RESULTS
03/11/2026 - 11:58 PM
ACCELERATOR
MODEL
112
tokens/s
generation
670
ms
time to first token
1859
tokens/s
prompt
677
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
Apple M4 Pro 8P+4E
RAM
64GB
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 21:09:56 PST 2025; root:xnu-12377.61.12~1/RELEASE_ARM64_T6041
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
2210
tokens/s
127
tokens/s
471
ms
pp4096+tg256
1831
tokens/s
74.2
tokens/s
2.25
sec
pp2048+tg256
2110
tokens/s
102
tokens/s
981
ms
pp2048+tg768
2079
tokens/s
98.0
tokens/s
995
ms
pp1024+tg1024
2226
tokens/s
115
tokens/s
468
ms
pp1280+tg3072
2192
tokens/s
91.0
tokens/s
592
ms
pp384+tg1152
2161
tokens/s
127
tokens/s
185
ms
pp64+tg1024
1439
tokens/s
140
tokens/s
51
ms
pp16+tg1536
482
tokens/s
133
tokens/s
41
ms