TEST #3579 RESULTS
05/20/2026 - 8:23 PM
ACCELERATOR
MODEL
171
tokens/s
generation
368
ms
time to first token
3301
tokens/s
prompt
1153
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
4187
tokens/s
184
tokens/s
250
ms
pp4096+tg256
3415
tokens/s
118
tokens/s
1.21
sec
pp2048+tg256
3772
tokens/s
155
tokens/s
549
ms
pp2048+tg768
3864
tokens/s
153
tokens/s
536
ms
pp1024+tg1024
3872
tokens/s
176
tokens/s
270
ms
pp1280+tg3072
3917
tokens/s
144
tokens/s
332
ms
pp384+tg1152
3934
tokens/s
196
tokens/s
102
ms
pp64+tg1024
2155
tokens/s
211
tokens/s
34
ms
pp16+tg1536
595
tokens/s
202
tokens/s
31
ms