TEST #3852 RESULTS
07/02/2026 - 7:30 PM
ACCELERATOR
MODEL
24.8
tokens/s
generation
4.97
sec
time to first token
254
tokens/s
prompt
108
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
25.3.0
Architecture
arm64
Version
Cosmopolitan 3.9.7 MODE=aarch64; Darwin Kernel Version 25.3.0: Wed Jan 28 20:51:28 PST 2026; root:xnu-12377.91.3~2/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
33.6
tokens/s
3.05
sec
pp4096+tg256
274
tokens/s
18.7
tokens/s
15.03
sec
pp2048+tg256
260
tokens/s
22.4
tokens/s
7.93
sec
pp2048+tg768
257
tokens/s
22.0
tokens/s
8.03
sec
pp1024+tg1024
267
tokens/s
24.1
tokens/s
3.88
sec
pp1280+tg3072
266
tokens/s
21.3
tokens/s
4.85
sec
pp384+tg1152
273
tokens/s
26.3
tokens/s
1.45
sec
pp64+tg1024
247
tokens/s
27.6
tokens/s
293
ms
pp16+tg1536
104
tokens/s
26.9
tokens/s
188
ms