TEST #3449 RESULTS
05/05/2026 - 5:09 PM
ACCELERATOR
MODEL
72.3
tokens/s
generation
1.14
sec
time to first token
1047
tokens/s
prompt
405
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
Apple M1 Pro 6P+2E
RAM
32GB
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 20:53:15 PST 2026; root:xnu-12377.81.4~5/RELEASE_ARM64_T6000
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
1288
tokens/s
81.7
tokens/s
807
ms
pp4096+tg256
1103
tokens/s
47.8
tokens/s
3.73
sec
pp2048+tg256
1242
tokens/s
65.3
tokens/s
1.66
sec
pp2048+tg768
1241
tokens/s
62.5
tokens/s
1.66
sec
pp1024+tg1024
1221
tokens/s
73.7
tokens/s
851
ms
pp1280+tg3072
1270
tokens/s
58.6
tokens/s
1.02
sec
pp384+tg1152
1195
tokens/s
83.2
tokens/s
332
ms
pp64+tg1024
681
tokens/s
90.9
tokens/s
104
ms
pp16+tg1536
181
tokens/s
86.4
tokens/s
98
ms