TEST #1521 RESULTS
09/15/2025 - 9:33 PM
ACCELERATOR
MODEL
181
tokens/s
generation
295
ms
time to first token
4072
tokens/s
prompt
1358
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
25.0.0
Architecture
arm64
Version
Cosmopolitan 3.9.7 MODE=aarch64; Darwin Kernel Version 25.0.0: Mon Aug 25 21:17:54 PDT 2025; root:xnu-12377.1.9~3/RELEASE_ARM64_T6041
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
5121
tokens/s
204
tokens/s
205
ms
pp4096+tg256
4257
tokens/s
124
tokens/s
970
ms
pp2048+tg256
4760
tokens/s
164
tokens/s
436
ms
pp2048+tg768
4860
tokens/s
158
tokens/s
428
ms
pp1024+tg1024
5005
tokens/s
185
tokens/s
210
ms
pp1280+tg3072
4984
tokens/s
149
tokens/s
262
ms
pp384+tg1152
4633
tokens/s
208
tokens/s
87
ms
pp64+tg1024
2399
tokens/s
225
tokens/s
30
ms
pp16+tg1536
633
tokens/s
215
tokens/s
29
ms