TEST #1900 RESULTS
12/03/2025 - 1:58 AM
ACCELERATOR
MODEL
185
tokens/s
generation
305
ms
time to first token
3883
tokens/s
prompt
1330
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
24.6.0
Architecture
arm64
Version
Cosmopolitan 3.9.7 MODE=aarch64; Darwin Kernel Version 24.6.0: Mon Aug 11 21:15:09 PDT 2025; root:xnu-11417.140.69.701.11~1/RELEASE_ARM64_T6041
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
4846
tokens/s
208
tokens/s
216
ms
pp4096+tg256
4127
tokens/s
124
tokens/s
1.00
sec
pp2048+tg256
4716
tokens/s
168
tokens/s
440
ms
pp2048+tg768
4701
tokens/s
161
tokens/s
442
ms
pp1024+tg1024
4886
tokens/s
189
tokens/s
214
ms
pp1280+tg3072
4749
tokens/s
151
tokens/s
275
ms
pp384+tg1152
4362
tokens/s
212
tokens/s
92
ms
pp64+tg1024
2009
tokens/s
232
tokens/s
36
ms
pp16+tg1536
551
tokens/s
218
tokens/s
33
ms