TEST #6 RESULTS
03/19/2025 - 10:13 PM
ACCELERATOR
MODEL
184
tokens/s
generation
301
ms
time to first token
3893
tokens/s
prompt
1336
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
24.3.0
Architecture
arm64
Version
Cosmopolitan 3.9.7 MODE=aarch64; Darwin Kernel Version 24.3.0: Thu Jan 2 20:24:22 PST 2025; root:xnu-11215.81.4~3/RELEASE_ARM64_T6041
RUNTIME
Name
llamafile
Version
0.9.1
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
5078
tokens/s
207
tokens/s
206
ms
pp4096+tg256
4214
tokens/s
125
tokens/s
980
ms
pp2048+tg256
4858
tokens/s
167
tokens/s
427
ms
pp2048+tg768
4696
tokens/s
161
tokens/s
442
ms
pp1024+tg1024
4836
tokens/s
189
tokens/s
217
ms
pp1280+tg3072
4954
tokens/s
150
tokens/s
264
ms
pp384+tg1152
4152
tokens/s
211
tokens/s
97
ms
pp64+tg1024
1759
tokens/s
230
tokens/s
40
ms
pp16+tg1536
490
tokens/s
217
tokens/s
36
ms