---
license: apache-2.0
base_model: Jackrong/Qwopus3.6-35B-A3B-Coder
base_model_relation: quantized
library_name: mlx
pipeline_tag: image-text-to-text
tags:
- mlx
- mlx-vlm
- mxfp8
- safetensors
- lm-studio
- apple-silicon
- qwen3_5_moe
- qwen3_6
- coder
- agent
- tool-use
- function-calling
- vision
- thinking-off
- abliterated
---

# qwopus3.6-35b-a3b-coder-abliterated-mxfp8-vision-mlx

Vision-enabled MLX MXFP8 conversion of [Jackrong/Qwopus3.6-35B-A3B-Coder](https://huggingface.co/Jackrong/Qwopus3.6-35B-A3B-Coder), prepared by Shiftedx for Apple Silicon, MLX, and LM Studio.

## Build Notes

- Quantized primary language weights with `mxfp8` at group size 32.
- Kept MoE router and gate modules in affine 8-bit group size 64 for compatibility.
- Added Qwen3.5/Qwen3.6-MoE-compatible vision components and validated image grounding locally.
- Removed source MTP tensors and set MTP/next-token prediction layer counts to 0 for LM Studio compatibility.
- Set `tool_parser_type` to `qwen3_coder`.
- Patched the chat template so `enable_thinking` defaults to false when the runtime honors that template variable.
- Applied a research refusal-direction weight edit using residual-direction orthogonalization.

## Local Validation

Validated locally on June 30, 2026 and July 1, 2026 with LM Studio and direct MLX/VLM loading.

| Check | Result |
|---|---|
| LM Studio load | Passed at 32k context, parallel 1, GPU max. |
| Basic text completion | Passed; answered `2+2` with `4` and stopped. |
| Code completion | Passed; produced a simple valid `add(a, b)` function. |
| Direct MLX/VLM image color smoke | Passed; answered `Red`. |
| Direct MLX/VLM OCR smoke | Passed; answered `FABLE 42`. |
| LM Studio OpenAI-compatible image smoke | Passed; answered `Red` and `FABLE 42`. |
| LM Studio native image smoke | Passed; answered `Red` and `FABLE 42`. |
| Thinking-off behavior | Smoke checks returned `0` reasoning tokens. |
| LM Studio logs | No warnings, errors, tracebacks, KV-cache issues, or tokenizer-regex warnings in the validation window. |

This is a smoke-validated release, not a full benchmark suite. Broader downstream evaluation is still recommended for production use.

## Recommended LM Studio Defaults

After downloading in LM Studio, load the model by repo name:

```bash
lms load shiftedx/qwopus3.6-35b-a3b-coder-abliterated-mxfp8-vision-mlx --context-length 32768 --parallel 1 --gpu max
```

Recommended profile defaults:

- Preset/template: Qwen3 thinking-compatible Jinja template with `<|im_end|>` stop.
- Thinking: off by default through the included chat template.
- Context length: `200000` when memory allows; `32768` was used for local validation.
- Sampling: temperature `0.6`, top-k `20`, top-p `0.95`, min-p enabled at `0`.
- Repeat penalty: off by default.
- Load: parallel `1`, GPU `max`.

## Provenance

- Publisher: Shiftedx
- Source model: https://huggingface.co/Jackrong/Qwopus3.6-35B-A3B-Coder
- Source license: Apache-2.0
- Quantization date: June 29, 2026
- Vision validation completed: July 1, 2026
- No MTP or draft-model tensors are included.