314 MB

Ctrl+K

1 contributor

major revision: runtime dominates (MTPLX 3.79x vs oMLX 54.6 t/s on the same artifact); void the FP16-vs-4bit conclusion as runtime-confounded; add contract-parameter verification; correct the oMLX depth claim

7161354 verified 5 days ago

.gitattributes

1.52 kB
initial commit 5 days ago
README.md

12 kB
major revision: runtime dominates (MTPLX 3.79x vs oMLX 54.6 t/s on the same artifact); void the FP16-vs-4bit conclusion as runtime-confounded; add contract-parameter verification; correct the oMLX depth claim 5 days ago
graft_mtp.py

6.14 kB
MTP head graft for MLX Qwen3.8-27B quantizations that dropped theirs 5 days ago
qwen3.8-27b-mtp-4bit.safetensors

314 MB
xet

MTP head graft for MLX Qwen3.8-27B quantizations that dropped theirs 5 days ago