TEST #1434 RESULTS
08/27/2025 - 7:41 PM
ACCELERATOR
MODEL
21.0
tokens/s
generation
6.14
sec
time to first token
202
tokens/s
prompt
88
LocalScore
HOW YOU STACK UP
Explore All ResultsMeta Llama 3.1 8B Instruct - Q4_K - Medium
SYSTEM
CPU
Apple M1 Pro 8P+2E
RAM
16GB
OS
Darwin
Kernel Release
24.6.0
Architecture
arm64
Version
Cosmopolitan 3.9.7 MODE=aarch64; Darwin Kernel Version 24.6.0: Mon Jul 14 11:30:29 PDT 2025; root:xnu-11417.140.69~1/RELEASE_ARM64_T6000
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
223
tokens/s
22.7
tokens/s
4.64
sec
pp4096+tg256
212
tokens/s
17.3
tokens/s
19.37
sec
pp2048+tg256
225
tokens/s
21.0
tokens/s
9.14
sec
pp2048+tg768
225
tokens/s
20.5
tokens/s
9.14
sec
pp1024+tg1024
230
tokens/s
22.6
tokens/s
4.50
sec
pp1280+tg3072
215
tokens/s
16.1
tokens/s
6.00
sec
pp384+tg1152
211
tokens/s
21.9
tokens/s
1.87
sec
pp64+tg1024
195
tokens/s
23.5
tokens/s
365
ms
pp16+tg1536
79
tokens/s
23.6
tokens/s
240
ms