TEST #392 RESULTS
04/06/2025 - 4:36 PM
ACCELERATOR
MODEL
186
tokens/s
generation
311
ms
time to first token
3699
tokens/s
prompt
1304
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
4819
tokens/s
205
tokens/s
217
ms
pp4096+tg256
4156
tokens/s
126
tokens/s
993
ms
pp2048+tg256
4653
tokens/s
170
tokens/s
446
ms
pp2048+tg768
4722
tokens/s
163
tokens/s
439
ms
pp1024+tg1024
4624
tokens/s
191
tokens/s
226
ms
pp1280+tg3072
4597
tokens/s
153
tokens/s
283
ms
pp384+tg1152
3869
tokens/s
215
tokens/s
103
ms
pp64+tg1024
1368
tokens/s
233
tokens/s
51
ms
pp16+tg1536
484
tokens/s
222
tokens/s
37
ms