Instructions to use abnormalmapstudio/Qwen3-Next-80B-A3B-Thinking-mxfp4-mlx with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use abnormalmapstudio/Qwen3-Next-80B-A3B-Thinking-mxfp4-mlx 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("abnormalmapstudio/Qwen3-Next-80B-A3B-Thinking-mxfp4-mlx")

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 abnormalmapstudio/Qwen3-Next-80B-A3B-Thinking-mxfp4-mlx with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "abnormalmapstudio/Qwen3-Next-80B-A3B-Thinking-mxfp4-mlx"

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": "abnormalmapstudio/Qwen3-Next-80B-A3B-Thinking-mxfp4-mlx"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

OpenClaw new

How to use abnormalmapstudio/Qwen3-Next-80B-A3B-Thinking-mxfp4-mlx with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "abnormalmapstudio/Qwen3-Next-80B-A3B-Thinking-mxfp4-mlx"

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 "abnormalmapstudio/Qwen3-Next-80B-A3B-Thinking-mxfp4-mlx" \
  --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 abnormalmapstudio/Qwen3-Next-80B-A3B-Thinking-mxfp4-mlx with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "abnormalmapstudio/Qwen3-Next-80B-A3B-Thinking-mxfp4-mlx"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "abnormalmapstudio/Qwen3-Next-80B-A3B-Thinking-mxfp4-mlx"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "abnormalmapstudio/Qwen3-Next-80B-A3B-Thinking-mxfp4-mlx",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

Hermes Agent

How to use abnormalmapstudio/Qwen3-Next-80B-A3B-Thinking-mxfp4-mlx 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 "abnormalmapstudio/Qwen3-Next-80B-A3B-Thinking-mxfp4-mlx"

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 abnormalmapstudio/Qwen3-Next-80B-A3B-Thinking-mxfp4-mlx

Run Hermes

hermes

Qwen3-Next-80B-A3B-Thinking-mxfp4-mlx / README.md

abnormalmapstudio

Add MLX 4-bit (mxfp4) quantized checkpoint and configs

88c66ae 11 months ago

preview code

Raw

History Blame

2.79 kB

	---
	license: apache-2.0
	library_name: mlx
	pipeline_tag: text-generation
	base_model: Qwen/Qwen3-Next-80B-A3B-Thinking
	tags:
	- mlx
	- qwen3_next
	- 4-bit
	- mxfp4
	- text-generation
	quantization_config:
	bits: 4
	mode: mxfp4
	group_size: 32
	model-index:
	- name: Qwen3-Next-80B-A3B-Thinking mxfp4 (MLX 4-bit)
	results: []
	---

	# Qwen3-Next-80B-A3B-Thinking — MLX 4-bit (mxfp4)

	This repository provides an Apple MLX-optimized 4-bit mxfp4 quantized checkpoint of the base model
	`Qwen/Qwen3-Next-80B-A3B-Thinking` for fast, memory‑efficient local inference on Apple Silicon.

	Key details
	- Format: MLX runtime, safetensors sharded weights
	- Quantization: mxfp4, group_size=32 with selective 8‑bit gates
	- Task: text generation / chat
	- Tokenizer: provided via `tokenizer.json` (BPE) with `chat_template.jinja`

	## Files
	- `model-0000X-of-00009.safetensors` and `model.safetensors.index.json` — weights (LFS)
	- `config.json` — architecture and quantization keys for MLX loaders
	- `tokenizer.json`, `tokenizer_config.json`, `vocab.json`, `merges.txt`, `added_tokens.json`, `special_tokens_map.json`
	- `chat_template.jinja` — chat formatting for multi‑turn prompts
	- `generation_config.json` — sensible default generation params
	- `LICENSE` — Apache-2.0

	## Usage (MLX)
	Install MLX-LM and run generation:

	```bash
	pip install mlx-lm
	```

	```python
	from mlx_lm import load, generate

	# Replace with your repo id once pushed
	repo_id = "<your-username>/Qwen3-Next-80B-A3B-Thinking-mxfp4-mlx"

	model, tokenizer = load(repo_id)

	messages = [
	{"role": "system", "content": "You are a helpful assistant."},
	{"role": "user", "content": "Explain what mxfp4 quantization is in one paragraph."},
	]

	prompt = tokenizer.apply_chat_template(
	messages, tokenize=False, add_generation_prompt=True
	)

	out = generate(
	model,
	tokenizer,
	prompt,
	max_tokens=512,
	temp=0.7,
	top_p=0.95,
	)
	print(out)
	```

	CLI example:

	```bash
	mlx_lm.generate --model "<your-username>/Qwen3-Next-80B-A3B-Thinking-mxfp4-mlx" \
	--prompt "List 5 creative dinner ideas." --max-tokens 200
	```

	## Hardware Notes
	- Apple Silicon recommended (M2/M3). The 4‑bit checkpoint reduces memory pressure significantly, but 80B‑class models still require substantial VRAM and system RAM. For best results, ensure macOS swap is available and limit `max_tokens` accordingly.

	## License
	- License: Apache-2.0 (this quantized packaging). See `LICENSE`.
	- Base model: `Qwen/Qwen3-Next-80B-A3B-Thinking` (see its model card for upstream license and usage terms). Ensure your use complies with the base model’s license.

	## Attribution
	If you use this model, please credit the upstream Qwen team and note that this is an MLX 4‑bit mxfp4 quantized derivative for Apple Silicon.