TEST #2266 RESULTS
01/12/2026 - 10:29 PM
ACCELERATOR
MODEL
33.0
tokens/s
generation
3.37
sec
time to first token
367
tokens/s
prompt
153
LocalScore
HOW YOU STACK UP
Explore All ResultsMeta Llama 3.1 8B Instruct - Q4_K - Medium
SYSTEM
CPU
Apple M4 Pro 10P+4E
RAM
48GB
OS
Darwin
Kernel Release
25.2.0
Architecture
arm64
Version
Cosmopolitan 3.9.7 MODE=aarch64; Darwin Kernel Version 25.2.0: Tue Nov 18 21:09:56 PST 2025; root:xnu-12377.61.12~1/RELEASE_ARM64_T6041
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
418
tokens/s
36.0
tokens/s
2.48
sec
pp4096+tg256
383
tokens/s
25.3
tokens/s
10.73
sec
pp2048+tg256
405
tokens/s
31.2
tokens/s
5.08
sec
pp2048+tg768
404
tokens/s
30.4
tokens/s
5.10
sec
pp1024+tg1024
415
tokens/s
33.7
tokens/s
2.50
sec
pp1280+tg3072
413
tokens/s
29.1
tokens/s
3.13
sec
pp384+tg1152
413
tokens/s
36.1
tokens/s
957
ms
pp64+tg1024
330
tokens/s
37.9
tokens/s
219
ms
pp16+tg1536
126
tokens/s
36.9
tokens/s
152
ms