TEST #1360 RESULTS
08/12/2025 - 12:12 AM
ACCELERATOR
MODEL
178
tokens/s
generation
227
ms
time to first token
4999
tokens/s
prompt
1578
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
Apple M3 Ultra 24P+8E
RAM
256GB
OS
Darwin
Kernel Release
24.6.0
Architecture
arm64
Version
Cosmopolitan 3.9.7 MODE=aarch64; Darwin Kernel Version 24.6.0: Thu Jul 31 21:25:54 PDT 2025; root:xnu-11417.140.69.701.6~1/RELEASE_ARM64_T6031
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
6175
tokens/s
194
tokens/s
171
ms
pp4096+tg256
6001
tokens/s
123
tokens/s
692
ms
pp2048+tg256
6725
tokens/s
162
tokens/s
311
ms
pp2048+tg768
6679
tokens/s
156
tokens/s
313
ms
pp1024+tg1024
6541
tokens/s
178
tokens/s
161
ms
pp1280+tg3072
6431
tokens/s
149
tokens/s
206
ms
pp384+tg1152
4635
tokens/s
206
tokens/s
87
ms
pp64+tg1024
1453
tokens/s
222
tokens/s
49
ms
pp16+tg1536
355
tokens/s
210
tokens/s
49
ms