---
license: apache-2.0
base_model: Jackrong/Qwopus3.6-35B-A3B-Coder
tags:
  - gguf
  - quantized
  - apex
  - moe
  - mixture-of-experts
  - qwen3
  - vlm
  - vision
  - coder
  - code
---

<!-- apex-banner-v2 -->
<div style="background-color: #f59e0b; color: white; padding: 20px; border-radius: 10px; text-align: center; margin: 20px 0;">
<h2 style="color: white; margin: 0 0 10px 0;">⚡ Each donation = another big MoE quantized</h2>
<p style="font-size: 18px; margin: 0 0 15px 0;">I host <b>30+ free APEX MoE quantizations</b> as independent research. My only local hardware is an <b>NVIDIA DGX Spark</b> (122 GB unified memory) — enough for ~30-50B-class MoEs, but <b>bigger ones (200B+) require rented compute</b> on H100/H200/Blackwell, typically $20-100 per quant.<br>If APEX quants are useful to you, your support directly funds those bigger runs.</p>
<p style="font-size: 20px; margin: 0;">
<a href="https://www.patreon.com/cw/mudler" style="color: white; text-decoration: underline;">🎉 Patreon (Monthly)</a> &nbsp;|&nbsp;
<a href="https://www.buymeacoffee.com/mudler" style="color: white; text-decoration: underline;">☕ Buy Me a Coffee</a> &nbsp;|&nbsp;
<a href="https://github.com/sponsors/mudler" style="color: white; text-decoration: underline;">⭐ GitHub Sponsors</a>
</p>
</div>

# Qwopus3.6-35B-A3B-Coder — APEX GGUF

**APEX (Adaptive Precision for EXpert Models)** quantizations of [Jackrong/Qwopus3.6-35B-A3B-Coder](https://huggingface.co/Jackrong/Qwopus3.6-35B-A3B-Coder) — a Qwen3.6-35B-A3B MoE tuned for coding.

**Brought to you by the [LocalAI](https://github.com/mudler/LocalAI) team** | [APEX Project](https://github.com/mudler/apex-quant) | [Technical Report](https://github.com/mudler/apex-quant/blob/main/paper/APEX_Technical_Report.pdf)

> This model ships an MTP head — for self-speculative decoding out of the box, see the MTP-bundled repo: [mudler/Qwopus3.6-35B-A3B-Coder-APEX-MTP-GGUF](https://huggingface.co/mudler/Qwopus3.6-35B-A3B-Coder-APEX-MTP-GGUF).

## Available Files

| File | Profile | Best For |
|------|---------|----------|
| Qwopus3.6-35B-A3B-Coder-APEX-I-Balanced.gguf | I-Balanced | Best overall — imatrix-enhanced |
| Qwopus3.6-35B-A3B-Coder-APEX-I-Quality.gguf | I-Quality | Highest quality with imatrix |
| Qwopus3.6-35B-A3B-Coder-APEX-Quality.gguf | Quality | Highest quality (no imatrix) |
| Qwopus3.6-35B-A3B-Coder-APEX-Balanced.gguf | Balanced | General purpose |
| Qwopus3.6-35B-A3B-Coder-APEX-I-Compact.gguf | I-Compact | Consumer GPUs, imatrix-enhanced |
| Qwopus3.6-35B-A3B-Coder-APEX-Compact.gguf | Compact | Consumer GPUs |
| Qwopus3.6-35B-A3B-Coder-APEX-I-Mini.gguf | I-Mini | Smallest viable, fastest inference |
| mmproj.gguf | Vision projector | Required for image understanding |

## What is APEX?

APEX is a quantization strategy for Mixture-of-Experts (MoE) models. It classifies tensors by role (routed expert, shared expert, attention) and applies a layer-wise precision gradient — edge layers (first/last 5) get higher precision, middle layers get more aggressive compression. I-variants use diverse imatrix calibration (chat, code, reasoning, tool-calling, agentic traces, Wikipedia).

See the [APEX project](https://github.com/mudler/apex-quant) for full details.

## Architecture

- **Model**: Qwopus3.6-35B-A3B-Coder (Qwen3_5MoeForConditionalGeneration, Qwen3.6-35B-A3B base)
- **Layers**: 40 · **Experts**: 256 routed + 1 shared (8 active) · **Total/Active**: ~35B / ~3B
- **Attention**: Hybrid (full attention every 4th layer, linear otherwise)
- **Vision**: Built-in vision encoder (mmproj included)
- **Calibration**: v1.3 diverse dataset

## Run with LocalAI

```bash
local-ai run mudler/Qwopus3.6-35B-A3B-Coder-APEX-GGUF@Qwopus3.6-35B-A3B-Coder-APEX-I-Balanced.gguf
```

## Credits

APEX is brought to you by the [LocalAI](https://github.com/mudler/LocalAI) team. Built on [llama.cpp](https://github.com/ggerganov/llama.cpp). Base model by [Jackrong](https://huggingface.co/Jackrong).