Downloads · 30 days
6
25% of all-time downloads
Hy-MT2-1.8B-SpecDraft-30B-Q3_K_M-MLX
QianheChen01/Hy-MT2-1.8B-SpecDraft-30B-Q3_K_M-MLX
Hy-MT2-1.8B-SpecDraft-30B-Q3_K_M-MLX is a machine learning model from QianheChen01. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
Converted from alphaZimuth/Hy-MT2-1.8B-SpecDraft-30B/Hy-MT2-1.8B-SpecDraft-30B-Q3KM.gguf for MLX/oMLX speculative decoding.
All-time downloads
24
Public
Parameters
266M
951 MB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors951 MB · 99%
Parameter types
How the weights are stored.
U32210M · 79%
Model card
From the Hugging Face model README
Hy-MT2-1.8B-SpecDraft-30B-Q3_K_M MLX
Converted from alphaZimuth/Hy-MT2-1.8B-SpecDraft-30B/Hy-MT2-1.8B-SpecDraft-30B-Q3_K_M.gguf for MLX/oMLX speculative decoding.
The checkpoint is a standard tied-embedding hunyuan_v1_dense model with the source GGUF precision tiers mapped to MLX affine modules using group size 64. Quantization parameters and ordinary floating weights use BF16.
Source tensor types: {'F32': 129, 'Q3_K': 128, 'Q4_K': 92, 'Q5_K': 4, 'Q6_K': 1}.
- Type
- hunyuan_v1_dense
- Created
- Aug 23, 2026
- Updated
- Aug 23, 2026