Instructions to use mlx-community/Hy3-oQ2e-2.37bpw with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mlx-community/Hy3-oQ2e-2.37bpw 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("mlx-community/Hy3-oQ2e-2.37bpw")

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 mlx-community/Hy3-oQ2e-2.37bpw with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "mlx-community/Hy3-oQ2e-2.37bpw"

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": "mlx-community/Hy3-oQ2e-2.37bpw"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use mlx-community/Hy3-oQ2e-2.37bpw 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 "mlx-community/Hy3-oQ2e-2.37bpw"

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 mlx-community/Hy3-oQ2e-2.37bpw

Run Hermes

hermes

OpenClaw new

How to use mlx-community/Hy3-oQ2e-2.37bpw with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "mlx-community/Hy3-oQ2e-2.37bpw"

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 "mlx-community/Hy3-oQ2e-2.37bpw" \
  --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 mlx-community/Hy3-oQ2e-2.37bpw with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "mlx-community/Hy3-oQ2e-2.37bpw"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "mlx-community/Hy3-oQ2e-2.37bpw"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "mlx-community/Hy3-oQ2e-2.37bpw",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

Hy3 (MLX, oQ2e @ 2.37 bpw)

Calibrated 2-bit MLX quantization of tencent/Hy3 (Hunyuan 3.0, 295B-A21B MoE), produced with omlx oQe at level 2. Effective 2.37 bits/weight over quantizable weights, 87.7 GB on disk. Targets Apple Silicon.

This is a shell-reduced variant of mlx-community/Hy3-oQ2e: the routed experts are identical, but the non-expert layers (attention, embeddings, lm_head) are quantized below the 8-bit that oQ2e keeps, trading a small amount of quality for ~2 GB.

Quantization layout

Component	oQ2e (parent)	This model (2.37 bpw)
Routed experts (98%)	2-bit gs128 + imatrix	2-bit gs128 + imatrix
Attention	8-bit gs64	6-bit gs128
Embeddings / lm_head	8-bit gs64	4-bit gs128

Routed experts are bit-for-bit the same as oQ2e (imatrix reused from the same calibration cache). Only the shell changed.

How it was quantized

Built from the BF16 source (~550 GB / 591 GiB) with omlx oQ level 2 + imatrix weighting. To stay within 128 GB RAM: the sensitivity pass reused the existing oQ2 quantization instead of building a full-precision proxy, and the importance matrix was reused from the oQ2e calibration cache. Streamed tensor-by-tensor.

Requirements

Runs natively in oMLX. For mlx-lm, hy_v3 support is pending upstream; until then:

uv pip install "mlx-lm @ git+https://github.com/kernelpool/mlx-lm.git@add-hy3-preview"

Benchmarks (all Hy3 MLX variants)

oMLX intelligence suite, 300 seeded samples per benchmark, identical questions across models. I ran seeded samples — this is not a complete benchmark run, so read the differences as noise and test the versions against your own workload before picking one.

Benchmark (300)	oQ2 · 2.68	oQ2e · 2.43	oQ2e-2.37bpw (this model)	oQ2e-2.33bpw	oQ2e-2.31bpw
mathqa	0.63	0.65	0.64	0.62	0.60
mmlu_pro	0.65	0.61	0.60	0.59	0.55
winogrande	0.74	0.68	0.68	0.65	0.65

Variants: oQ2 · oQ2e · oQ2e-2.37bpw · oQ2e-2.33bpw · oQ2e-2.31bpw

Usage

python -m mlx_lm generate --model mlx-community/Hy3-oQ2e-2.37bpw \
  --prompt "Explain Bayes' theorem in two sentences." --max-tokens 300

from mlx_lm import load, generate
model, tokenizer = load("mlx-community/Hy3-oQ2e-2.37bpw")

License

Apache-2.0, inherited from tencent/Hy3.

Downloads last month: -

Safetensors

Model size

24B params

Tensor type

BF16

U32

F32

MLX

Hardware compatibility

2-bit

Model tree for mlx-community/Hy3-oQ2e-2.37bpw

Base model

tencent/Hy3

Quantized

(56)

this model

Collection including mlx-community/Hy3-oQ2e-2.37bpw

Hy3

Collection

MLX versions of Hy3 • 5 items • Updated about 11 hours ago