Instructions to use ulises-c/Qwen3.5-9B-MTP-8bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ulises-c/Qwen3.5-9B-MTP-8bit 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("ulises-c/Qwen3.5-9B-MTP-8bit")

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 ulises-c/Qwen3.5-9B-MTP-8bit with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "ulises-c/Qwen3.5-9B-MTP-8bit"

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "mlx-lm": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "ulises-c/Qwen3.5-9B-MTP-8bit"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

MLX LM

How to use ulises-c/Qwen3.5-9B-MTP-8bit with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "ulises-c/Qwen3.5-9B-MTP-8bit"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "ulises-c/Qwen3.5-9B-MTP-8bit"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "ulises-c/Qwen3.5-9B-MTP-8bit",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

Hermes Agent

How to use ulises-c/Qwen3.5-9B-MTP-8bit 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 "ulises-c/Qwen3.5-9B-MTP-8bit"

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 ulises-c/Qwen3.5-9B-MTP-8bit

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use ulises-c/Qwen3.5-9B-MTP-8bit with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "ulises-c/Qwen3.5-9B-MTP-8bit"

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 "ulises-c/Qwen3.5-9B-MTP-8bit" \
  --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"

Qwen3.5-9B-MTP-8bit / README.md

ulises-c

Document compatible MLX target models (8bit/6bit)

801e45b verified 3 months ago

preview code

Raw History Blame Contribute Delete

2.7 kB

	---
	language:
	- en
	license: apache-2.0
	base_model:
	- Qwen/Qwen3.5-9B
	- mlx-community/Qwen3.5-9B-MTP-bf16
	library_name: mlx
	pipeline_tag: text-generation
	tags:
	- mlx
	- mlx-vlm
	- qwen3_5_mtp
	- qwen3.5
	- qwen3.5-9b
	- qwen
	- mtp
	- speculative-decoding
	- draft-model
	- 8bit
	- quantized
	inference: false
	---

	# Qwen3.5-9B-MTP-8bit

	This repository contains 8-bit quantized Multi-Token Prediction (MTP) drafter weights for `Qwen/Qwen3.5-9B`, for use with `mlx-vlm` speculative decoding. It was quantized from [`mlx-community/Qwen3.5-9B-MTP-bf16`](https://huggingface.co/mlx-community/Qwen3.5-9B-MTP-bf16).

	This is not a standalone chat or text-generation model. Load it as the draft model alongside a compatible Qwen3.5 9B target checkpoint.

	## Compatible target models

	Pair this drafter with a Qwen3.5-9B target checkpoint. Recommended MLX targets (match target precision to your memory budget):

	- [`mlx-community/Qwen3.5-9B-8bit`](https://huggingface.co/mlx-community/Qwen3.5-9B-8bit) — recommended pairing for this 8-bit drafter
	- [`mlx-community/Qwen3.5-9B-6bit`](https://huggingface.co/mlx-community/Qwen3.5-9B-6bit)

	## Use with mlx-vlm

	```bash
	uv run mlx_vlm.generate \
	--model mlx-community/Qwen3.5-9B-8bit \
	--draft-model ulises-c/Qwen3.5-9B-MTP-8bit \
	--prompt "Hi, how are you?" \
	--max-tokens 256 \
	--enable-thinking
	```

	For local weights:

	```bash
	uv run mlx_vlm.generate \
	--model /path/to/target-model \
	--draft-model /path/to/Qwen3.5-9B-MTP-8bit \
	--prompt "Hi, how are you?" \
	--max-tokens 256 \
	--enable-thinking
	```

	## Model Details

	- Model type: `qwen3_5_mtp`
	- MTP block size: `2`
	- Target architecture: Qwen3.5 9B
	- Precision: 8-bit (affine, group size 64) — 8.501 bits per weight
	- Runtime: MLX / `mlx-vlm`
	- Format: Safetensors with MLX-compatible config and tokenizer files

	## Conversion

	Quantized with `mlx-vlm` (the `qwen3_5_mtp` architecture is provided by `mlx-vlm`, not `mlx-lm`):

	```bash
	uvx --from 'mlx-vlm @ git+https://github.com/Blaizzy/mlx-vlm' mlx_vlm.convert \
	--hf-path mlx-community/Qwen3.5-9B-MTP-bf16 \
	--mlx-path Qwen3.5-9B-MTP-8bit \
	-q --q-bits 8 --q-group-size 64
	```

	## Intended Use

	Use this repo only as a speculative decoding drafter for compatible Qwen3.5 9B checkpoints. The target model verifies drafted tokens, while this MTP model proposes candidate tokens per decoding step.

	## Limitations

	This checkpoint requires runtime support for Qwen/DeepSeek MTP draft models in `mlx-vlm`. Standard standalone generation through generic Transformers APIs is not expected to work with this repository by itself.

	Please refer to the upstream `Qwen/Qwen3.5-9B` model card and license terms for model usage constraints.