Downloads · 30 days
0
Qwen3.6-27B-MTP-mlx
exolabs/Qwen3.6-27B-MTP-mlx
Qwen3.6-27B-MTP-mlx is a machine learning model from exolabs. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
The raw mtp. tensors extracted from exolabs/qwen3.6-35b-a3b-2.06gb-mtp-fp4-mirror, bf16 — just the MTP block, none of the target weights. exo-nvidia's MLX speculative-decoding path (SpeculativeStrategy.kind == 'mtp')…
Access
Public
Updated May 29, 2026
Parameters
425M
849 MB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors849 MB · 100%
At a glance
- Access
- Public
- Created
- May 29, 2026
- Updated
- May 29, 2026
- SHA
- 1aa115a4
Model card
From the Hugging Face model README
Qwen3.6 MTP head (MLX)
The raw mtp.* tensors extracted from exolabs/qwen3.6-35b-a3b-2.06gb-mtp-fp4-mirror, bf16 — just the MTP block, none of the target weights. exo-nvidia's MLX speculative-decoding path (SpeculativeStrategy.kind == 'mtp') loads these and sanitises them at load time (the +1.0 norm shift, gate/up split and per-expert stack are applied by the runtime, not here).
- Created
- May 29, 2026
- Updated
- May 29, 2026