TEST #3696 RESULTS
06/06/2026 - 7:10 PM
ACCELERATOR
MODEL
165
tokens/s
generation
373
ms
time to first token
3112
tokens/s
prompt
1112
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
Apple M4 Max 10P+4E
RAM
36GB
OS
Darwin
Kernel Release
25.5.0
Architecture
arm64
Version
Cosmopolitan 3.9.7 MODE=aarch64; Darwin Kernel Version 25.5.0: Mon Apr 27 20:41:15 PDT 2026; root:xnu-12377.121.6~2/RELEASE_ARM64_T6041
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
4159
tokens/s
182
tokens/s
252
ms
pp4096+tg256
3413
tokens/s
117
tokens/s
1.21
sec
pp2048+tg256
3790
tokens/s
152
tokens/s
547
ms
pp2048+tg768
3895
tokens/s
146
tokens/s
532
ms
pp1024+tg1024
3878
tokens/s
168
tokens/s
269
ms
pp1280+tg3072
4075
tokens/s
138
tokens/s
320
ms
pp384+tg1152
3058
tokens/s
187
tokens/s
131
ms
pp64+tg1024
1377
tokens/s
201
tokens/s
51
ms
pp16+tg1536
362
tokens/s
192
tokens/s
49
ms