Instructions to use majentik/Qwen3-Coder-Next-MLX-2bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use majentik/Qwen3-Coder-Next-MLX-2bit with MLX:

# Make sure mlx-lm is installed
# pip install --upgrade mlx-lm

# Generate text with mlx-lm
from mlx_lm import load, generate

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

prompt = "Write a story about Einstein"
messages = [{"role": "user", "content": prompt}]
prompt = tokenizer.apply_chat_template(
    messages, add_generation_prompt=True
)

text = generate(model, tokenizer, prompt=prompt, verbose=True)

Notebooks
Google Colab
Kaggle
Local Apps Settings
LM Studio

How to use majentik/Qwen3-Coder-Next-MLX-2bit with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "majentik/Qwen3-Coder-Next-MLX-2bit"

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "mlx-lm": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "majentik/Qwen3-Coder-Next-MLX-2bit"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use majentik/Qwen3-Coder-Next-MLX-2bit with Hermes Agent:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "majentik/Qwen3-Coder-Next-MLX-2bit"

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default majentik/Qwen3-Coder-Next-MLX-2bit

Run Hermes

hermes

OpenClaw new

How to use majentik/Qwen3-Coder-Next-MLX-2bit with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "majentik/Qwen3-Coder-Next-MLX-2bit"

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "majentik/Qwen3-Coder-Next-MLX-2bit" \
  --custom-provider-id mlx-lm \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

MLX LM

How to use majentik/Qwen3-Coder-Next-MLX-2bit with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "majentik/Qwen3-Coder-Next-MLX-2bit"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "majentik/Qwen3-Coder-Next-MLX-2bit"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "majentik/Qwen3-Coder-Next-MLX-2bit",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

Qwen3-Coder-Next-MLX-2bit / README.md

majentik

Qwen3-Coder-Next MLX 2-bit (rev a7fbcb5)

6431829 verified 12 days ago

preview code

Raw

History Blame Contribute Delete

2.73 kB

	---
	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).