TEST #1256 RESULTS
07/25/2025 - 10:24 PM
ACCELERATOR
MODEL
190
tokens/s
generation
297
ms
time to first token
3952
tokens/s
prompt
1362
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
24.5.0
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
5011
tokens/s
213
tokens/s
209
ms
pp4096+tg256
4313
tokens/s
128
tokens/s
957
ms
pp2048+tg256
4782
tokens/s
173
tokens/s
434
ms
pp2048+tg768
4829
tokens/s
166
tokens/s
430
ms
pp1024+tg1024
4919
tokens/s
194
tokens/s
213
ms
pp1280+tg3072
4873
tokens/s
155
tokens/s
268
ms
pp384+tg1152
4347
tokens/s
217
tokens/s
93
ms
pp64+tg1024
1952
tokens/s
237
tokens/s
37
ms
pp16+tg1536
539
tokens/s
225
tokens/s
33
ms