TEST #3695 RESULTS
06/06/2026 - 6:49 PM
ACCELERATOR
MODEL
165
tokens/s
generation
367
ms
time to first token
3234
tokens/s
prompt
1133
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
4143
tokens/s
183
tokens/s
252
ms
pp4096+tg256
3428
tokens/s
117
tokens/s
1.20
sec
pp2048+tg256
3851
tokens/s
152
tokens/s
538
ms
pp2048+tg768
3928
tokens/s
146
tokens/s
528
ms
pp1024+tg1024
4069
tokens/s
168
tokens/s
257
ms
pp1280+tg3072
3862
tokens/s
139
tokens/s
337
ms
pp384+tg1152
3856
tokens/s
187
tokens/s
104
ms
pp64+tg1024
1409
tokens/s
201
tokens/s
50
ms
pp16+tg1536
561
tokens/s
192
tokens/s
33
ms