TEST #184 RESULTS
04/01/2025 - 11:55 PM
ACCELERATOR
MODEL
68.6
tokens/s
generation
1.14
sec
time to first token
1068
tokens/s
prompt
400
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
Apple M1 Pro 8P+2E
RAM
32GB
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
1293
tokens/s
79.7
tokens/s
804
ms
pp4096+tg256
1077
tokens/s
45.8
tokens/s
3.82
sec
pp2048+tg256
1237
tokens/s
63.8
tokens/s
1.67
sec
pp2048+tg768
1232
tokens/s
61.5
tokens/s
1.68
sec
pp1024+tg1024
1288
tokens/s
71.9
tokens/s
808
ms
pp1280+tg3072
1282
tokens/s
57.7
tokens/s
1.01
sec
pp384+tg1152
1233
tokens/s
78.6
tokens/s
322
ms
pp64+tg1024
726
tokens/s
82.9
tokens/s
99
ms
pp16+tg1536
243
tokens/s
75.2
tokens/s
76
ms