Hy4-flash MLX 4-bit with DFly2

Preview checkpoint. Weight conversion checks passed. TensorFold 1.2.9 rejects this architecture at startup. Generation, DFly2 parity, and runtime memory requirements are pending validation.

This is TensorFold’s MLX conversion of Tencent Hy4-flash, a multimodal model that takes text and images. Both variants include Tencent’s DFly2 drafter at source precision.

Tencent Hy

Choose a checkpoint

Checkpoint Weight files
This repo · MLX 4-bit 129.86 GB
MLX 8-bit 239.30 GB

These sizes are for stored weights. Runtime memory depends on the engine, context length, cache settings, and concurrent requests. Check the TensorFold releases for runtime support before downloading.

What’s included

Component Format
Target weights MLX affine 4-bit safetensors
Quantization group size 64 for most weights and 32 for Engram embeddings
DFly2 drafter Upstream weights and configuration at source precision
Vision tower and MoE router gates Source precision

The repo’s MTP suffix identifies the variant that bundles the DFly2 drafter. DFly2 requires the model’s sparse-attention index and KV cache.

Architecture

Tencent describes Hy4-flash as a multimodal mixture-of-experts model with 220 billion total parameters and about 12 billion active parameters per token. The language stack combines sliding-window attention, sparse attention and Engram embeddings. The upstream DFly2 drafter has five layers that reuse the target model's KV cache and sparse-attention positions.

Conversion and validation

The conversion uses Tencent's pinned BF16 checkpoint and retains the tokenizer, processor, chat template and DFly2 configuration. The 148 output shards match the tensor index, sampled packed weights match MLX affine quantization, and all 87 DFly2 tensors match the upstream bytes. Generation and drafted-versus-plain parity are pending runtime support.

Licence and attribution

The original model, DFly2 drafter and evaluations are the work of Tencent and the upstream contributors. TensorFold prepares the MLX conversion. The Tencent Hy License applies.

Downloads last month
-
Safetensors
Model size
220B params
Tensor type
U32
·
BF16
·
F32
·
I32
·
MLX
Hardware compatibility
Log In to add your hardware

4-bit

Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for TensorFold/Hy4-flash-MLX-4bit-MTP

Quantized
(8)
this model