TEST #1881 RESULTS
11/29/2025 - 7:53 AM
ACCELERATOR
MODEL
30.5
tokens/s
generation
4.15
sec
time to first token
302
tokens/s
prompt
130
LocalScore
HOW YOU STACK UP
Explore All ResultsMeta Llama 3.1 8B Instruct - Q4_K - Medium
SYSTEM
CPU
Apple M4 Pro 8P+4E
RAM
24GB
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
339
tokens/s
33.0
tokens/s
3.05
sec
pp4096+tg256
312
tokens/s
23.8
tokens/s
13.18
sec
pp2048+tg256
330
tokens/s
29.1
tokens/s
6.23
sec
pp2048+tg768
331
tokens/s
28.2
tokens/s
6.23
sec
pp1024+tg1024
339
tokens/s
31.1
tokens/s
3.05
sec
pp1280+tg3072
325
tokens/s
27.1
tokens/s
3.97
sec
pp384+tg1152
326
tokens/s
33.2
tokens/s
1.21
sec
pp64+tg1024
296
tokens/s
34.7
tokens/s
244
ms
pp16+tg1536
118
tokens/s
33.9
tokens/s
162
ms