TEST #2606 RESULTS
02/13/2026 - 8:01 PM
ACCELERATOR
MODEL
180
tokens/s
generation
298
ms
time to first token
3918
tokens/s
prompt
1333
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
25.2.0
Architecture
arm64
Version
Cosmopolitan 3.9.7 MODE=aarch64; Darwin Kernel Version 25.2.0: Tue Nov 18 21:09:56 PST 2025; root:xnu-12377.61.12~1/RELEASE_ARM64_T6041
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
5105
tokens/s
202
tokens/s
206
ms
pp4096+tg256
4307
tokens/s
123
tokens/s
959
ms
pp2048+tg256
4892
tokens/s
162
tokens/s
425
ms
pp2048+tg768
4784
tokens/s
157
tokens/s
434
ms
pp1024+tg1024
4853
tokens/s
183
tokens/s
216
ms
pp1280+tg3072
4836
tokens/s
148
tokens/s
270
ms
pp384+tg1152
4313
tokens/s
206
tokens/s
93
ms
pp64+tg1024
1649
tokens/s
225
tokens/s
43
ms
pp16+tg1536
528
tokens/s
213
tokens/s
34
ms