TEST #3615 RESULTS
05/26/2026 - 12:26 PM
ACCELERATOR
MODEL
24.5
tokens/s
generation
5.68
sec
time to first token
224
tokens/s
prompt
99
LocalScore
HOW YOU STACK UP
Explore All ResultsMeta Llama 3.1 8B Instruct - Q4_K - Medium
SYSTEM
CPU
Apple M2 Pro 6P+4E
RAM
32GB
OS
Darwin
Kernel Release
25.5.0
Architecture
arm64
Version
Cosmopolitan 3.9.7 MODE=aarch64; Darwin Kernel Version 25.5.0: Mon Apr 27 20:39:09 PDT 2026; root:xnu-12377.121.6~2/RELEASE_ARM64_T6020
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
247
tokens/s
23.7
tokens/s
4.19
sec
pp4096+tg256
217
tokens/s
19.7
tokens/s
18.91
sec
pp2048+tg256
250
tokens/s
23.8
tokens/s
8.25
sec
pp2048+tg768
249
tokens/s
22.7
tokens/s
8.26
sec
pp1024+tg1024
249
tokens/s
25.3
tokens/s
4.15
sec
pp1280+tg3072
246
tokens/s
21.9
tokens/s
5.24
sec
pp384+tg1152
253
tokens/s
27.1
tokens/s
1.55
sec
pp64+tg1024
214
tokens/s
28.4
tokens/s
332
ms
pp16+tg1536
90
tokens/s
27.6
tokens/s
211
ms