TEST #934 RESULTS
05/23/2025 - 9:43 AM
ACCELERATOR
MODEL
179
tokens/s
generation
302
ms
time to first token
3896
tokens/s
prompt
1321
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
4944
tokens/s
199
tokens/s
212
ms
pp4096+tg256
4249
tokens/s
123
tokens/s
972
ms
pp2048+tg256
4713
tokens/s
163
tokens/s
441
ms
pp2048+tg768
4709
tokens/s
156
tokens/s
441
ms
pp1024+tg1024
4823
tokens/s
182
tokens/s
217
ms
pp1280+tg3072
4804
tokens/s
147
tokens/s
272
ms
pp384+tg1152
4367
tokens/s
204
tokens/s
92
ms
pp64+tg1024
1951
tokens/s
223
tokens/s
37
ms
pp16+tg1536
507
tokens/s
211
tokens/s
36
ms