TEST #3206 RESULTS
03/28/2026 - 7:04 PM
ACCELERATOR
MODEL
191
tokens/s
generation
301
ms
time to first token
3879
tokens/s
prompt
1351
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
25.3.0
Architecture
arm64
Version
Cosmopolitan 3.9.7 MODE=aarch64; Darwin Kernel Version 25.3.0: Wed Jan 28 20:51:28 PST 2026; root:xnu-12377.91.3~2/RELEASE_ARM64_T6041
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
5163
tokens/s
214
tokens/s
203
ms
pp4096+tg256
4288
tokens/s
129
tokens/s
963
ms
pp2048+tg256
4938
tokens/s
173
tokens/s
420
ms
pp2048+tg768
4805
tokens/s
166
tokens/s
432
ms
pp1024+tg1024
4592
tokens/s
196
tokens/s
228
ms
pp1280+tg3072
4580
tokens/s
157
tokens/s
285
ms
pp384+tg1152
4528
tokens/s
220
tokens/s
89
ms
pp64+tg1024
1620
tokens/s
239
tokens/s
43
ms
pp16+tg1536
395
tokens/s
228
tokens/s
44
ms