TEST #1252 RESULTS
07/25/2025 - 4:05 AM
ACCELERATOR
MODEL
179
tokens/s
generation
309
ms
time to first token
3731
tokens/s
prompt
1293
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
Apple M4 Max 12P+4E
RAM
48GB
OS
Darwin
Kernel Release
24.5.0
Architecture
arm64
Version
Cosmopolitan 3.9.7 MODE=aarch64; Darwin Kernel Version 24.5.0: Tue Apr 22 19:53:27 PDT 2025; root:xnu-11417.121.6~2/RELEASE_ARM64_T6041
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
4979
tokens/s
199
tokens/s
211
ms
pp4096+tg256
4224
tokens/s
123
tokens/s
978
ms
pp2048+tg256
4640
tokens/s
163
tokens/s
447
ms
pp2048+tg768
4584
tokens/s
156
tokens/s
453
ms
pp1024+tg1024
4575
tokens/s
183
tokens/s
229
ms
pp1280+tg3072
4888
tokens/s
148
tokens/s
267
ms
pp384+tg1152
3857
tokens/s
205
tokens/s
104
ms
pp64+tg1024
1451
tokens/s
224
tokens/s
48
ms
pp16+tg1536
379
tokens/s
211
tokens/s
46
ms