---
base_model: Qwen/Qwen3-Coder-Next
library_name: mlx
tags:
  - qwen
  - qwen3-coder-next
  - moe
  - coding
  - agentic
  - quantized
  - mlx
  - 2bit
license: apache-2.0
pipeline_tag: text-generation
---

# Qwen3-Coder-Next - MLX 2-bit

**2-bit weight-quantized MLX version** of [Qwen/Qwen3-Coder-Next](https://huggingface.co/Qwen/Qwen3-Coder-Next),
Qwen's 80B-A3B agentic coding MoE (512 experts, 10 active; hybrid Gated DeltaNet +
Gated Attention; 256k context). Only ~3B parameters are active per token, so it runs
far faster than its 80B total suggests. Converted with `mlx_lm` — the canonical MLX
runtime for `qwen3_next` — and smoke-verified (chat + code probes) on Apple Silicon
with this exact payload before publishing. See `PROVENANCE.md`.

Approximate model size: **~25 GB**

## Model Specifications

| Property | Value |
|---|---|
| **Base Model** | [Qwen/Qwen3-Coder-Next](https://huggingface.co/Qwen/Qwen3-Coder-Next) |
| **Parameters** | 80 billion total (~3 billion active per token) |
| **Architecture** | MoE, hybrid Gated DeltaNet + Gated Attention (`qwen3_next`) |
| **Modality** | Text-only (code-focused) |
| **Context Length** | 256k tokens |
| **License** | Apache 2.0 |
| **Weight Quantization** | 2-bit affine, group size 64 (~25 GB) |
| **Framework** | MLX (Apple Silicon), `mlx-lm >= 0.31` |

## Quickstart

```python
from mlx_lm import load, generate

model, tokenizer = load("majentik/Qwen3-Coder-Next-MLX-2bit")

prompt = tokenizer.apply_chat_template(
    [{"role": "user", "content": "Write a Python function that merges two sorted lists."}],
    add_generation_prompt=True, tokenize=False,
)
print(generate(model, tokenizer, prompt=prompt, max_tokens=512))
```

Or from the command line:

```bash
mlx_lm.generate --model majentik/Qwen3-Coder-Next-MLX-2bit --prompt "Refactor this function ..."
```

## Variants in this family

| Variant | Approx size | Use case |
|---|---|---|
| **2bit**(https://huggingface.co/majentik/Qwen3-Coder-Next-MLX-2bit) | ~25 GB | Smallest; quality floor |
| [3bit](https://huggingface.co/majentik/Qwen3-Coder-Next-MLX-3bit) | ~34 GB | Low-RAM Macs |
| [4bit](https://huggingface.co/majentik/Qwen3-Coder-Next-MLX-4bit) | ~43 GB | Balanced default |
| [5bit](https://huggingface.co/majentik/Qwen3-Coder-Next-MLX-5bit) | ~53 GB | Higher fidelity |
| [6bit](https://huggingface.co/majentik/Qwen3-Coder-Next-MLX-6bit) | ~62 GB | Near-8bit quality |
| [8bit](https://huggingface.co/majentik/Qwen3-Coder-Next-MLX-8bit) | ~81 GB | Reference fidelity |

Smoke verification covers load + short-form generation quality gates only;
it is not a benchmark. For maximum fidelity use the largest variant that
fits your unified memory (leave ~20% headroom for KV cache).