Tess-4-27B Abliterated MXFP4 Vision MTPLX

This is the MTPLX 2.0.1 wrapper for the Tess-4-27B abliterated MXFP4 vision MLX artifact. It includes the standard MLX/VLM body, the BF16 vision tower, and a native MTP sidecar for MTPLX speculative decoding.

Use the paired standard MLX repo when you want stock MLX-VLM or LM Studio compatibility without MTPLX.

Source

  • Base model: migtissera/Tess-4-27B
  • Source revision: ab2110bec1702f27a62f48f7e8929683a613c51d
  • Paired standard repo: Shiftedx/Tess-4-27B-Abliterated-MXFP4-Vision-MLX
  • License: Apache-2.0
  • Chat format: Qwen chat template with <think> reasoning blocks

Contents

  • Runtime format: MLX plus MTPLX metadata
  • Quantization: MXFP4, 4-bit, group size 32
  • Vision tower: BF16 vision tensors grafted from the source model
  • Vision tensor count: 333
  • MTP sidecar: mtp.safetensors
  • MTP tensor count: 15
  • MTPLX version used for validation: 2.0.1

MTPLX Validation

mtplx inspect --require-mtp passed locally after contract cleanup. The artifact is marked as native MTPLX-compatible.

Tune summary on Apple M4 Max, 64 GB unified memory, fans on auto:

Mode Decode tok/s Multiplier vs AR Acceptance
AR 28.09 1.00x n/a
D1 46.28 1.65x 0.979
D2 50.68 1.80x 0.970, 0.954
D3 42.20 1.50x 0.869, 0.717, 0.593

Recommended MTPLX depth: 2.

Abliteration Notes

The selected candidate used residual-direction weight orthogonalization against a Tess-specific refusal direction.

Setting Value
Strength 2.5
Targets attention, dense_down
Edited modules 128
Direction scope global
Preserve column norm true

Heldout screen, no code execution:

Variant Refusal rate Benign refusal rate Utility pass rate Avg generation tok/s
Parent MXFP4 1.00 0.00 1.00 23.91
Selected strength 2.5 0.00 0.00 1.00 24.22
Strength 3.0 trial 0.00 0.00 0.50 26.20

Strength 2.5 was selected because the 3.0 trial harmed utility in the heldout screen.

Vision Validation

mlx_vlm.generate smoke passed locally after the vision graft. The smoke image was described as:

A close-up of a white ceramic mug with a black handle, filled with dark coffee and topped with a swirl of foam.

BenchLocal Light Screen

Pack Pass / Total Score Failed IDs
toolcall-15 11/15 73% TC-03, TC-07, TC-11, TC-12
instructfollow-15 14/15 93% IF-14
Total 25/30 83%

Important caveat: this was a non-canonical quick run with thinking disabled, max_tokens=2048, and timeout_per_case=90. It is a fast quality screen, not directly comparable to the upstream model-card full BenchLocal score of 122/150 for Tess-4-27B Q8.

Usage

Inspect:

mtplx inspect --require-mtp Shiftedx/Tess-4-27B-Abliterated-MXFP4-Vision-MTPLX

Serve with the validated depth:

mtplx serve \
  --model Shiftedx/Tess-4-27B-Abliterated-MXFP4-Vision-MTPLX \
  --generation-mode mtp \
  --load-mtp \
  --depth 2 \
  --profile sustained \
  --reasoning off

For stock MLX-VLM or LM Studio usage, prefer Shiftedx/Tess-4-27B-Abliterated-MXFP4-Vision-MLX.

Limitations

  • MTPLX speed numbers are local to the validation host and prompt mix.
  • Vision was validated with MLX-VLM locally. Always run a small smoke test in the exact app/runtime you plan to use.
  • This is an ablated research artifact, not a safety guarantee. Evaluate behavior before deployment.
Downloads last month
94
Safetensors
Model size
27B params
Tensor type
U8
·
U32
·
BF16
·
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 Shiftedx/Tess-4-27B-Abliterated-MXFP4-Vision-MTPLX

Base model

Qwen/Qwen3.6-27B
Quantized
(37)
this model

Collection including Shiftedx/Tess-4-27B-Abliterated-MXFP4-Vision-MTPLX