TEST #412 RESULTS
04/06/2025 - 7:21 PM
ACCELERATOR
MODEL
72.9
tokens/s
generation
1.12
sec
time to first token
1070
tokens/s
prompt
412
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
Apple M1 Pro 6P+2E
RAM
16GB
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
1313
tokens/s
82.9
tokens/s
792
ms
pp4096+tg256
1133
tokens/s
48.3
tokens/s
3.63
sec
pp2048+tg256
1245
tokens/s
65.8
tokens/s
1.66
sec
pp2048+tg768
1262
tokens/s
63.0
tokens/s
1.64
sec
pp1024+tg1024
1283
tokens/s
74.2
tokens/s
810
ms
pp1280+tg3072
1284
tokens/s
59.0
tokens/s
1.01
sec
pp384+tg1152
1219
tokens/s
83.8
tokens/s
325
ms
pp64+tg1024
685
tokens/s
91.7
tokens/s
103
ms
pp16+tg1536
202
tokens/s
87.3
tokens/s
89
ms