TEST #16 RESULTS
03/24/2025 - 8:59 PM
ACCELERATOR
MODEL
80.0
tokens/s
generation
1.01
sec
time to first token
1192
tokens/s
prompt
456
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
1467
tokens/s
91.3
tokens/s
709
ms
pp4096+tg256
1249
tokens/s
53.7
tokens/s
3.30
sec
pp2048+tg256
1406
tokens/s
72.0
tokens/s
1.47
sec
pp2048+tg768
1409
tokens/s
69.4
tokens/s
1.47
sec
pp1024+tg1024
1453
tokens/s
80.8
tokens/s
716
ms
pp1280+tg3072
1379
tokens/s
64.6
tokens/s
940
ms
pp384+tg1152
1403
tokens/s
91.8
tokens/s
283
ms
pp64+tg1024
732
tokens/s
101
tokens/s
96
ms
pp16+tg1536
228
tokens/s
95.8
tokens/s
79
ms