Instructions to use XavierLocalAI/Hy3-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use XavierLocalAI/Hy3-4bit 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("XavierLocalAI/Hy3-4bit")

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 XavierLocalAI/Hy3-4bit with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "XavierLocalAI/Hy3-4bit"

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": "XavierLocalAI/Hy3-4bit"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use XavierLocalAI/Hy3-4bit 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 "XavierLocalAI/Hy3-4bit"

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 XavierLocalAI/Hy3-4bit

Run Hermes

hermes

OpenClaw new

How to use XavierLocalAI/Hy3-4bit with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "XavierLocalAI/Hy3-4bit"

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 "XavierLocalAI/Hy3-4bit" \
  --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 XavierLocalAI/Hy3-4bit with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "XavierLocalAI/Hy3-4bit"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "XavierLocalAI/Hy3-4bit"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "XavierLocalAI/Hy3-4bit",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

Hy3-4bit / README.md

XavierLocalAI

Add files using upload-large-folder tool

c4f3e2d verified 6 days ago

preview code

Raw

History Blame Contribute Delete

2.57 kB

	---
	license: apache-2.0
	base_model: tencent/Hy3
	base_model_relation: quantized
	tags:
	- mlx
	- hunyuan
	- hy3
	- moe
	pipeline_tag: text-generation
	library_name: mlx
	---

	# Hy3-4bit (MLX)

	A clean 4-bit MLX quantization of [tencent/Hy3](https://huggingface.co/tencent/Hy3) (Hunyuan 3.0, Apache-2.0), converted with `mlx-lm` and verified running on Apple Silicon.

	Hy3 is a 295B-parameter Mixture-of-Experts model with 21B active parameters, 80 layers, 192 routed experts (top-8) plus one shared expert, a native MTP (multi-token-prediction) head, and 256K context.

	## Why this quant is clean

	Naive uniform 4-bit quantization degrades MoE models badly, because the router that picks which experts fire is precision-sensitive. This build follows a mixed-precision recipe:

	- 4-bit (group size 64, affine) for attention and expert weights
	- 8-bit for every MoE router gate (`*.mlp.router.gate`)
	- MTP head preserved

	That router protection is the difference between a coherent model and mush, and it matches the recipe used by the reference `mlx-community/Hy3-preview-4bit`.

	## Footprint

	- Weights: ~166 GB
	- Fits: two 128GB Apple Silicon machines (or one 192GB+ Mac), does not fit a single 128GB machine at 4-bit.

	## How it was made

	```python
	from mlx_lm.convert import convert

	def hy3_predicate(path, module, config=None):
	if path.endswith("mlp.router.gate"):
	return {"group_size": 64, "bits": 8}
	return {"group_size": 64, "bits": 4}

	convert(
	hf_path="tencent/Hy3",
	mlx_path="Hy3-4bit",
	quantize=True, q_bits=4, q_group_size=64, q_mode="affine",
	quant_predicate=hy3_predicate,
	)
	```

	`hy_v3` architecture support comes from [mlx-lm PR #1211](https://github.com/ml-explore/mlx-lm/pull/1211).

	## Benchmarks (2x M5 Max, Thunderbolt RDMA)

	Measured on two M5 Max (128GB each), pipeline-parallel over Thunderbolt with Apple's `jaccl` RDMA backend (`MLX_METAL_FAST_SYNCH=1`). Single-stream decode.

	\| Metric \| Value \|
	\|---\|---\|
	\| Decode (generation) \| 36.91 tok/s \|
	\| Prompt (prefill) \| 8.6 tok/s \|
	\| Peak memory / node \| 84.4 GB \|
	\| Backend \| jaccl (RDMA), pipeline-parallel \|

	Notes: at 4-bit (~166GB) the model does not fit a single 128GB machine, so this is a genuine 2-node cluster run. The `ring`/TCP backend trips the macOS Metal command-buffer watchdog on the cross-node fence wait; RDMA (`jaccl`) is required for stable single-stream decode.

	## Credits

	- Base model: Tencent Hunyuan (`tencent/Hy3`, Apache-2.0)
	- Architecture support: mlx-lm PR #1211
	- Quantization + Apple Silicon cluster benchmark: bicVanYonk