TEST #1490 RESULTS
09/08/2025 - 4:53 PM
ACCELERATOR
MODEL
115
tokens/s
generation
581
ms
time to first token
2109
tokens/s
prompt
748
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
Apple M4 Pro 10P+4E
RAM
24GB
OS
Darwin
Kernel Release
24.6.0
Architecture
arm64
Version
Cosmopolitan 3.9.7 MODE=aarch64; Darwin Kernel Version 24.6.0: Mon Jul 14 11:30:40 PDT 2025; root:xnu-11417.140.69~1/RELEASE_ARM64_T6041
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
2614
tokens/s
134
tokens/s
399
ms
pp4096+tg256
2116
tokens/s
76.8
tokens/s
1.95
sec
pp2048+tg256
2476
tokens/s
106
tokens/s
837
ms
pp2048+tg768
2477
tokens/s
101
tokens/s
836
ms
pp1024+tg1024
2604
tokens/s
120
tokens/s
401
ms
pp1280+tg3072
2360
tokens/s
93.5
tokens/s
551
ms
pp384+tg1152
2391
tokens/s
128
tokens/s
167
ms
pp64+tg1024
1459
tokens/s
143
tokens/s
50
ms
pp16+tg1536
489
tokens/s
137
tokens/s
38
ms