TEST #501 RESULTS
04/07/2025 - 3:56 PM
ACCELERATOR
MODEL
179
tokens/s
generation
308
ms
time to first token
3814
tokens/s
prompt
1305
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
24.4.0
Architecture
arm64
Version
Cosmopolitan 3.9.7 MODE=aarch64; Darwin Kernel Version 24.4.0: Wed Mar 19 21:17:35 PDT 2025; root:xnu-11417.101.15~1/RELEASE_ARM64_T6041
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
4960
tokens/s
200
tokens/s
211
ms
pp4096+tg256
4186
tokens/s
122
tokens/s
987
ms
pp2048+tg256
4755
tokens/s
163
tokens/s
437
ms
pp2048+tg768
4595
tokens/s
157
tokens/s
452
ms
pp1024+tg1024
4655
tokens/s
182
tokens/s
225
ms
pp1280+tg3072
4866
tokens/s
148
tokens/s
268
ms
pp384+tg1152
3959
tokens/s
206
tokens/s
101
ms
pp64+tg1024
2004
tokens/s
224
tokens/s
36
ms
pp16+tg1536
343
tokens/s
213
tokens/s
51
ms