Tess-4-27B-Abliterated-MXFP4-Vision-MTPLX

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

Tess-4-27B-Abliterated-MXFP4-Vision-MTPLX is a image-text-to-text model from Shiftedx. Use it for the image-text-to-text task on the model card, and read the license before you ship it in a product. It is set up for mlx. The card lists the license as apache-2.0.

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.

Downloads · 30 days

7% of all-time downloads

All-time downloads

519

Public

Parameters

27.4B

16.1 GB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors16.1 GB · 100%

Parameter types

How the weights are stored.

U3226.9B · 98%

Try a prompt

Base models

migtissera/Tess-4-27B

Model card

From the Hugging Face model README

Tess-4-27B Abliterated MXFP4 Vision MTPLX

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

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	Utility pass rate	Avg generation tok/s
Parent MXFP4	1.00	1.00	23.91
Selected strength 2.5	0.00	1.00	24.22
Strength 3.0 trial	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.

Task: Image-Text-to-Text
Library: mlx
Type: qwen3_5
License: apache-2.0
Created: Jul 10, 2026
Updated: Jul 10, 2026