TEST #3215 RESULTS
03/29/2026 - 4:34 PM
ACCELERATOR
MODEL
118
tokens/s
generation
575
ms
time to first token
2116
tokens/s
prompt
757
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
25.3.0
Architecture
arm64
Version
Cosmopolitan 3.9.7 MODE=aarch64; Darwin Kernel Version 25.3.0: Wed Jan 28 20:51:28 PST 2026; root:xnu-12377.91.3~2/RELEASE_ARM64_T6041
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
2646
tokens/s
133
tokens/s
394
ms
pp4096+tg256
2122
tokens/s
77.0
tokens/s
1.94
sec
pp2048+tg256
2503
tokens/s
106
tokens/s
827
ms
pp2048+tg768
2509
tokens/s
101
tokens/s
825
ms
pp1024+tg1024
2562
tokens/s
120
tokens/s
407
ms
pp1280+tg3072
2553
tokens/s
95.1
tokens/s
509
ms
pp384+tg1152
2141
tokens/s
136
tokens/s
186
ms
pp64+tg1024
1503
tokens/s
149
tokens/s
48
ms
pp16+tg1536
503
tokens/s
143
tokens/s
38
ms