TEST #827 RESULTS
05/05/2025 - 10:29 PM
ACCELERATOR
MODEL
106
tokens/s
generation
682
ms
time to first token
1684
tokens/s
prompt
640
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
Apple M1 Max 8P+2E
RAM
64GB
OS
Darwin
Kernel Release
24.4.0
Architecture
arm64
Version
Cosmopolitan 3.9.7 MODE=aarch64; Darwin Kernel Version 24.4.0: Fri Apr 11 18:33:47 PDT 2025; root:xnu-11417.101.15~117/RELEASE_ARM64_T6000
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
2183
tokens/s
118
tokens/s
478
ms
pp4096+tg256
1921
tokens/s
73.0
tokens/s
2.15
sec
pp2048+tg256
2064
tokens/s
97.2
tokens/s
1.00
sec
pp2048+tg768
2102
tokens/s
93.4
tokens/s
984
ms
pp1024+tg1024
2050
tokens/s
108
tokens/s
508
ms
pp1280+tg3072
2071
tokens/s
88.1
tokens/s
627
ms
pp384+tg1152
1812
tokens/s
121
tokens/s
219
ms
pp64+tg1024
749
tokens/s
131
tokens/s
92
ms
pp16+tg1536
205
tokens/s
125
tokens/s
85
ms