This is a mixed-precision MLX quantization of apetersson/DeepSeek-V4-Flash-0731-Abliterated-FP8, designed to run on a 128 GB Apple Silicon system. Weight files occupy about 99.46 GiB.

Quantization profile

Tensor class	Storage
Routed expert gate/up	affine 2-bit, group size 64, importance weighted
Routed expert down	affine 3-bit, group size 64, importance weighted
Attention projections	MXFP8, group size 32
Shared experts	MXFP8, group size 32
Output head	MXFP8, group size 32
Embeddings, routers, norms and auxiliary tensors	protected BF16/FP32

The importance matrix was imported from jedisct1/DeepSeek-V4-Flash-imatrix-aligned. The 129 routed modules have architecture-compatible dimensions, but this is an aligned transfer from the earlier DeepSeek-V4-Flash checkpoint, not a fresh 0731-native calibration run.

This variant omits the attached speculative weights and sets num_nextn_predict_layers=0. It is intended for standard trunk generation; it is not a DSpark release. The preferred local runtime is oMLX with DeepSeek-V4 support.

Validation status

All 21 shards and 1,931 indexed tensors passed structural validation.
The imported importance matrix was applied to all 129 routed modules.
The full paired refusal and capability benchmark is pending.

Limitations

This is an aggressive mixed 2/3-bit quantization. Quality should be measured against both the abliterated FP8 checkpoint and the clean quantized control. Abliteration can affect behavior beyond refusals and does not guarantee a particular response.

License and attribution

The upstream DeepSeek-V4-Flash-0731 weights are MIT licensed. This repository retains that license and documents both the abliteration and quantization provenance above.

apetersson/DeepSeek-V4-Flash-0731-Abliterated-MLX-Mixed-2bit-3bit-g64

DeepSeek-V4-Flash-0731 Abliterated MLX Mixed 2-bit/3-bit g64

Quantization profile

Validation status

Limitations

License and attribution

apetersson/
DeepSeek-V4-Flash-0731-Abliterated-MLX-Mixed-2bit-3bit-g64