TEST #3540 RESULTS
05/15/2026 - 6:18 AM
ACCELERATOR
MODEL
78.5
tokens/s
generation
1.01
sec
time to first token
1193
tokens/s
prompt
452
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
25.4.0
Architecture
arm64
Version
Cosmopolitan 3.9.7 MODE=aarch64; Darwin Kernel Version 25.4.0: Thu Mar 19 19:30:44 PDT 2026; root:xnu-12377.101.15~1/RELEASE_ARM64_T6000
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
1455
tokens/s
88.4
tokens/s
715
ms
pp4096+tg256
1242
tokens/s
52.5
tokens/s
3.32
sec
pp2048+tg256
1386
tokens/s
71.2
tokens/s
1.49
sec
pp2048+tg768
1387
tokens/s
68.3
tokens/s
1.49
sec
pp1024+tg1024
1424
tokens/s
80.1
tokens/s
730
ms
pp1280+tg3072
1439
tokens/s
64.1
tokens/s
901
ms
pp384+tg1152
1407
tokens/s
90.2
tokens/s
283
ms
pp64+tg1024
749
tokens/s
98.0
tokens/s
95
ms
pp16+tg1536
251
tokens/s
93.4
tokens/s
73
ms