TEST #3304 RESULTS
04/14/2026 - 3:16 AM
ACCELERATOR
MODEL
125
tokens/s
generation
559
ms
time to first token
2012
tokens/s
prompt
765
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
Apple M1 Max 8P+2E
RAM
32GB
OS
Darwin
Kernel Release
25.3.0
Architecture
arm64
Version
Cosmopolitan 3.9.7 MODE=aarch64; Darwin Kernel Version 25.3.0: Wed Jan 28 20:54:46 PST 2026; root:xnu-12377.91.3~2/RELEASE_ARM64_T6000
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
2674
tokens/s
138
tokens/s
390
ms
pp4096+tg256
2404
tokens/s
87.7
tokens/s
1.72
sec
pp2048+tg256
2576
tokens/s
115
tokens/s
804
ms
pp2048+tg768
2572
tokens/s
110
tokens/s
805
ms
pp1024+tg1024
2565
tokens/s
127
tokens/s
407
ms
pp1280+tg3072
2583
tokens/s
105
tokens/s
503
ms
pp384+tg1152
1959
tokens/s
141
tokens/s
203
ms
pp64+tg1024
601
tokens/s
152
tokens/s
113
ms
pp16+tg1536
176
tokens/s
145
tokens/s
97
ms