TEST #306 RESULTS
04/05/2025 - 10:57 PM
ACCELERATOR
MODEL
139
tokens/s
generation
419
ms
time to first token
2624
tokens/s
prompt
955
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
Apple M1 Ultra 16P+4E
RAM
128GB
OS
Darwin
Kernel Release
24.3.0
Architecture
arm64
Version
Cosmopolitan 3.9.7 MODE=aarch64; Darwin Kernel Version 24.3.0: Thu Jan 2 20:24:16 PST 2025; root:xnu-11215.81.4~3/RELEASE_ARM64_T6000
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
3350
tokens/s
151
tokens/s
312
ms
pp4096+tg256
3434
tokens/s
105
tokens/s
1.20
sec
pp2048+tg256
3558
tokens/s
131
tokens/s
583
ms
pp2048+tg768
3531
tokens/s
127
tokens/s
588
ms
pp1024+tg1024
3283
tokens/s
142
tokens/s
321
ms
pp1280+tg3072
3303
tokens/s
121
tokens/s
394
ms
pp384+tg1152
2326
tokens/s
154
tokens/s
171
ms
pp64+tg1024
645
tokens/s
163
tokens/s
105
ms
pp16+tg1536
188
tokens/s
158
tokens/s
91
ms