TEST #1007 RESULTS
06/06/2025 - 1:32 PM
ACCELERATOR
MODEL
184
tokens/s
generation
308
ms
time to first token
3776
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
128GB
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
4870
tokens/s
207
tokens/s
215
ms
pp4096+tg256
4184
tokens/s
124
tokens/s
987
ms
pp2048+tg256
4662
tokens/s
168
tokens/s
445
ms
pp2048+tg768
4684
tokens/s
158
tokens/s
443
ms
pp1024+tg1024
4724
tokens/s
188
tokens/s
222
ms
pp1280+tg3072
4674
tokens/s
151
tokens/s
279
ms
pp384+tg1152
4018
tokens/s
211
tokens/s
100
ms
pp64+tg1024
1665
tokens/s
230
tokens/s
42
ms
pp16+tg1536
503
tokens/s
218
tokens/s
35
ms