TEST #1795 RESULTS
11/13/2025 - 9:51 PM
ACCELERATOR
MODEL
20.2
tokens/s
generation
6.88
sec
time to first token
180
tokens/s
prompt
81
LocalScore
HOW YOU STACK UP
Explore All ResultsMeta Llama 3.1 8B Instruct - Q4_K - Medium
SYSTEM
CPU
Apple M1 Pro 6P+2E
RAM
16GB
OS
Darwin
Kernel Release
25.0.0
Architecture
arm64
Version
Cosmopolitan 3.9.7 MODE=aarch64; Darwin Kernel Version 25.0.0: Wed Sep 17 21:41:45 PDT 2025; root:xnu-12377.1.9~141/RELEASE_ARM64_T6000
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
202
tokens/s
22.0
tokens/s
5.10
sec
pp4096+tg256
189
tokens/s
15.8
tokens/s
21.75
sec
pp2048+tg256
198
tokens/s
19.3
tokens/s
10.37
sec
pp2048+tg768
199
tokens/s
18.8
tokens/s
10.36
sec
pp1024+tg1024
202
tokens/s
20.6
tokens/s
5.12
sec
pp1280+tg3072
197
tokens/s
17.9
tokens/s
6.53
sec
pp384+tg1152
197
tokens/s
22.0
tokens/s
2.00
sec
pp64+tg1024
165
tokens/s
22.9
tokens/s
429
ms
pp16+tg1536
68
tokens/s
22.3
tokens/s
275
ms