TEST #1188 RESULTS
07/07/2025 - 10:50 AM
ACCELERATOR
MODEL
180
tokens/s
generation
308
ms
time to first token
3858
tokens/s
prompt
1312
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
Apple M4 Max 12P+4E
RAM
48GB
OS
Darwin
Kernel Release
24.5.0
Architecture
arm64
Version
Cosmopolitan 3.9.7 MODE=aarch64; Darwin Kernel Version 24.5.0: Tue Apr 22 19:53:27 PDT 2025; root:xnu-11417.121.6~2/RELEASE_ARM64_T6041
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
4955
tokens/s
202
tokens/s
212
ms
pp4096+tg256
4096
tokens/s
122
tokens/s
1.01
sec
pp2048+tg256
4628
tokens/s
164
tokens/s
449
ms
pp2048+tg768
4647
tokens/s
158
tokens/s
447
ms
pp1024+tg1024
4853
tokens/s
184
tokens/s
216
ms
pp1280+tg3072
4771
tokens/s
148
tokens/s
273
ms
pp384+tg1152
4383
tokens/s
205
tokens/s
92
ms
pp64+tg1024
1851
tokens/s
224
tokens/s
39
ms
pp16+tg1536
536
tokens/s
213
tokens/s
34
ms