TEST #378 RESULTS
04/06/2025 - 2:37 PM
ACCELERATOR
MODEL
190
tokens/s
generation
304
ms
time to first token
3888
tokens/s
prompt
1345
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
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
4894
tokens/s
215
tokens/s
214
ms
pp4096+tg256
4182
tokens/s
128
tokens/s
987
ms
pp2048+tg256
4764
tokens/s
170
tokens/s
436
ms
pp2048+tg768
4745
tokens/s
164
tokens/s
437
ms
pp1024+tg1024
4806
tokens/s
193
tokens/s
218
ms
pp1280+tg3072
4581
tokens/s
155
tokens/s
284
ms
pp384+tg1152
4436
tokens/s
219
tokens/s
91
ms
pp64+tg1024
2030
tokens/s
239
tokens/s
36
ms
pp16+tg1536
552
tokens/s
227
tokens/s
33
ms