Instructions to use apus-ailab/APUS-OpenJev-v1-4B-MLX-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use apus-ailab/APUS-OpenJev-v1-4B-MLX-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("apus-ailab/APUS-OpenJev-v1-4B-MLX-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 apus-ailab/APUS-OpenJev-v1-4B-MLX-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 "apus-ailab/APUS-OpenJev-v1-4B-MLX-4bit"

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": "apus-ailab/APUS-OpenJev-v1-4B-MLX-4bit"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

MLX LM

How to use apus-ailab/APUS-OpenJev-v1-4B-MLX-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 "apus-ailab/APUS-OpenJev-v1-4B-MLX-4bit"

Run an OpenAI-compatible server

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

Hermes Agent

How to use apus-ailab/APUS-OpenJev-v1-4B-MLX-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 "apus-ailab/APUS-OpenJev-v1-4B-MLX-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 apus-ailab/APUS-OpenJev-v1-4B-MLX-4bit

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use apus-ailab/APUS-OpenJev-v1-4B-MLX-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 "apus-ailab/APUS-OpenJev-v1-4B-MLX-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 "apus-ailab/APUS-OpenJev-v1-4B-MLX-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"

APUS-OpenJev-v1-4B-MLX-4bit

English | 中文 · Source model · Collection · GGUF collection · MLX collection · MLX-8bit · GGUF / Ollama

MLX weights (mixed 4/6-bit affine (mlx-lm mixed_4_6), group size 64) of APUS-OpenJev-v1-4B for Apple Silicon Macs (mlx-lm, LM Studio).

OpenJev is a decision model: each request supplies a state, an instruction and 2–16 candidates, and the model scores candidate labels A–P. It is not a chat model.

Quick start

pip install mlx-lm
hf download apus-ailab/APUS-OpenJev-v1-4B-MLX-4bit --local-dir ./openjev
python ./openjev/examples/openjev_mlx.py --model ./openjev

examples/openjev_mlx.py renders prompts with openjev_contracts.py (the training contract) and returns the exact candidate distribution.

Parity

Frozen80 with identical prompt tokens, compared with the HF BF16 release (full depth, 66/80 · 82.50%):

Run / 运行	Backend / 后端	Frozen80	= HF BF16	Max Δp
NVIDIA RTX PRO 6000 (CUDA)	mlx 0.32.2 on Linux x86_64 (Device(gpu, 0))	67/80 · 83.75%	79/80	0.5980
Apple M5 24 GB (Metal)	mlx 0.32.2 on Darwin arm64 (Device(gpu, 0))	67/80 · 83.75%	79/80	0.5980

Verified on an Apple M5, 24 GB: peak memory 3.48 GB. The same file on CUDA and Metal gave identical decisions on 80/80 prompts (max Δp 0.043). Frozen80 is a reused development panel, not a blind benchmark. Per-question rows (candidate probabilities, choice, correctness; join with Frozen80 by panel_index): evaluation/per-question/.

Conversion

mlx-lm 0.31.3 / mlx 0.32.2; mixed 4/6-bit affine (mlx-lm mixed_4_6), group size 64.
6-bit lm_head and v_proj/down_proj in sensitive layers, 4-bit elsewhere (the MLX analogue of Q4_K_M); MoE router gates stay 8-bit (recipe). Calibrated DWQ/GPTQ were tried and were not practical for this hybrid-attention model on the conversion hardware.
GDN A_log and linear_attn.norm.weight keep their source precision (FP32 in the 35B release).
Full depth only, text only, probabilities not calibrated.