---
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
- mxfp8
- safetensors
- lm-studio
- apple-silicon
- qwen3_5_moe
- qwen3_6
- coder
- agent
- tool-use
- function-calling
- thinking-off
- vision
---

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

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

## What Changed

- Converted from the upstream safetensors checkpoint with the local streaming MLX pipeline.
- Quantized primary linear weights with `mxfp8` at group size 32.
- Kept MoE router/gate modules in affine 8-bit group size 64 for compatibility.
- 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 a runtime honors the template variable.
- Added grafted vision tensors from `model.visual.*` as `vision_tower.*`.

## Local Validation

Hardware reference: Apple M4 Max Apple Silicon with 64 GB unified memory.

Validated locally on June 29, 2026 with LM Studio server on port 8080, 32k context, parallel 1, GPU max.

| Check | Result |
|---|---|
| LM Studio load | Passed; 33.31 GiB in LM Studio at 32k context. |
| Basic text completion | Passed; returned `2+2=4` and stopped. |
| Vision image smoke | Experimental only: model loaded and stopped, but a simple shapes image was not fully reliable. MXFP4 misidentified the shapes/colors; MXFP8 identified shapes/colors but not left-to-right order. |


Note: LM Studio may still report hidden `reasoning_tokens` for this checkpoint even though the upstream model is intended for thinking-off use. Use adequate `max_tokens` for smoke tests.

## Vision Status

This variant includes a grafted Qwen vision tower from the source checkpoint. The tensor/key layout matches the working MLX Qwen3.5-MoE vision format, and `vision_tower.patch_embed.proj.weight` was transposed to MLX layout `(1152, 2, 16, 16, 3)`.

Local LM Studio image smoke testing did not fully pass, so treat the vision path as experimental. The language path loads and answers normally.

## LM Studio

After downloading in LM Studio, load the model key:

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

Recommended profile defaults, matching the local Shiftedx 35B AgentWorld/Ornith profiles:

- Preset/template: Qwen3 thinking-compatible Jinja template with `<|im_end|>` stop.
- Context length: `200000` when memory allows; `32768` was used for local smoke validation.
- Sampling: temperature `0.6`, top-k `20`, top-p `0.95`, min-p enabled at `0`.
- Repeat penalty: unchecked/off, value `1.1` if enabled manually.
- Load: parallel `1`, GPU `max`.

## Provenance

- Source model: https://huggingface.co/Jackrong/Qwopus3.6-35B-A3B-Coder
- Source license: Apache-2.0
- Quantization date: June 29, 2026