TEST #2360 RESULTS
01/27/2026 - 9:17 AM
ACCELERATOR
MODEL
118
tokens/s
generation
567
ms
time to first token
2135
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
64GB
OS
Darwin
Kernel Release
24.6.0
Architecture
arm64
Version
Cosmopolitan 3.9.7 MODE=aarch64; Darwin Kernel Version 24.6.0: Wed Nov 5 21:30:44 PST 2025; root:xnu-11417.140.69.705.2~1/RELEASE_ARM64_T6041
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
2696
tokens/s
133
tokens/s
387
ms
pp4096+tg256
2203
tokens/s
77.5
tokens/s
1.87
sec
pp2048+tg256
2488
tokens/s
106
tokens/s
832
ms
pp2048+tg768
2490
tokens/s
101
tokens/s
832
ms
pp1024+tg1024
2562
tokens/s
120
tokens/s
407
ms
pp1280+tg3072
2533
tokens/s
95.1
tokens/s
513
ms
pp384+tg1152
2664
tokens/s
136
tokens/s
150
ms
pp64+tg1024
1234
tokens/s
149
tokens/s
58
ms
pp16+tg1536
341
tokens/s
142
tokens/s
53
ms