Instructions to use apus-ailab/APUS-OpenJev-v1-4B-MLX-8bit 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-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("apus-ailab/APUS-OpenJev-v1-4B-MLX-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 apus-ailab/APUS-OpenJev-v1-4B-MLX-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 "apus-ailab/APUS-OpenJev-v1-4B-MLX-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": "apus-ailab/APUS-OpenJev-v1-4B-MLX-8bit"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

MLX LM

How to use apus-ailab/APUS-OpenJev-v1-4B-MLX-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 "apus-ailab/APUS-OpenJev-v1-4B-MLX-8bit"

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-8bit"
# 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-8bit",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

Hermes Agent

How to use apus-ailab/APUS-OpenJev-v1-4B-MLX-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 "apus-ailab/APUS-OpenJev-v1-4B-MLX-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 apus-ailab/APUS-OpenJev-v1-4B-MLX-8bit

Run Hermes

hermes

Atomic Chat

OpenClaw

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

APUS-OpenJev-v1-4B-MLX-8bit / README.md

gump2049

Add Frozen80 per-question results

40ef34e verified 10 days ago

preview code

Raw History Blame

2.87 kB

	---
	library_name: mlx
	license: apache-2.0
	base_model: apus-ailab/APUS-OpenJev-v1-4B
	base_model_relation: quantized
	pipeline_tag: text-generation
	language:
	- en
	- zh
	tags:
	- apus-openjev
	- decision-model
	- mlx
	- apple-silicon
	---

	# APUS-OpenJev-v1-4B-MLX-8bit

	[English](README.md) \| [中文](README.zh-CN.md) · [Source model](https://huggingface.co/apus-ailab/APUS-OpenJev-v1-4B) · [Collection](https://huggingface.co/collections/apus-ailab/apus-openjev-v1-6ab1ee888eb002fcdd3a2825) · [GGUF collection](https://huggingface.co/collections/apus-ailab/apus-openjev-v1-gguf-6ab39d5e724c4d8a1021198f) · [MLX collection](https://huggingface.co/collections/apus-ailab/apus-openjev-v1-mlx-6ab39d5fc988a1b1cb89dfc8) · [MLX-4bit](https://huggingface.co/apus-ailab/APUS-OpenJev-v1-4B-MLX-4bit) · [GGUF / Ollama](https://huggingface.co/apus-ailab/APUS-OpenJev-v1-4B-GGUF)

	MLX weights (8-bit affine, group size 64) of [APUS-OpenJev-v1-4B](https://huggingface.co/apus-ailab/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

	```bash
	pip install mlx-lm
	hf download apus-ailab/APUS-OpenJev-v1-4B-MLX-8bit --local-dir ./openjev
	python ./openjev/examples/openjev_mlx.py --model ./openjev
	```

	`examples/openjev_mlx.py` renders prompts with [openjev_contracts.py](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)) \| 66/80 · 82.50% \| 80/80 \| 0.1201 \|
	\| Apple M5 24 GB (Metal) \| mlx 0.32.2 on Darwin arm64 (Device(gpu, 0)) \| 66/80 · 82.50% \| 80/80 \| 0.1480 \|

	Verified on an Apple M5, 24 GB: peak memory 5.44 GB. The same file on CUDA and Metal gave identical decisions on 80/80 prompts (max Δp 0.054). 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/](evaluation/per-question/).

	## Conversion

	- mlx-lm `0.31.3` / mlx `0.32.2`; 8-bit affine, group size 64.
	- 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.

	## License

	Apache-2.0, inherited from the source model; see [LICENSE](LICENSE). Base model: [Qwen/Qwen3.5-4B](https://huggingface.co/Qwen/Qwen3.5-4B).

	Authors: gumpcheng ([xDAN2099](https://huggingface.co/xDAN2099)), zhangxu, [APUS AI-LAB](https://github.com/APUS-AI-Lab).