TEST #1893 RESULTS
11/30/2025 - 5:30 PM
ACCELERATOR
MODEL
121
tokens/s
generation
578
ms
time to first token
2123
tokens/s
prompt
763
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
Apple M4 Pro 10P+4E
RAM
48GB
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
2631
tokens/s
137
tokens/s
396
ms
pp4096+tg256
2112
tokens/s
78.0
tokens/s
1.95
sec
pp2048+tg256
2450
tokens/s
109
tokens/s
845
ms
pp2048+tg768
2474
tokens/s
103
tokens/s
837
ms
pp1024+tg1024
2586
tokens/s
123
tokens/s
403
ms
pp1280+tg3072
2562
tokens/s
96.9
tokens/s
507
ms
pp384+tg1152
2474
tokens/s
140
tokens/s
163
ms
pp64+tg1024
1390
tokens/s
154
tokens/s
52
ms
pp16+tg1536
433
tokens/s
146
tokens/s
42
ms