Instructions to use Edge0/Edge0-8B-A1B-preview with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Edge0/Edge0-8B-A1B-preview 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("Edge0/Edge0-8B-A1B-preview")

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 Edge0/Edge0-8B-A1B-preview with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "Edge0/Edge0-8B-A1B-preview"

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": "Edge0/Edge0-8B-A1B-preview"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

MLX LM

How to use Edge0/Edge0-8B-A1B-preview with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "Edge0/Edge0-8B-A1B-preview"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "Edge0/Edge0-8B-A1B-preview"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "Edge0/Edge0-8B-A1B-preview",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

Hermes Agent

How to use Edge0/Edge0-8B-A1B-preview 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 "Edge0/Edge0-8B-A1B-preview"

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 Edge0/Edge0-8B-A1B-preview

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use Edge0/Edge0-8B-A1B-preview with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "Edge0/Edge0-8B-A1B-preview"

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 "Edge0/Edge0-8B-A1B-preview" \
  --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"

Edge0-8B-A1B-preview / README.md

bupalinyu

Upload README.md

cadc35c verified 13 days ago

preview code

Raw History Blame Contribute Delete

7 kB

	---
	license: apache-2.0
	library_name: mlx
	tags:
	- moe
	- edge-inference
	- prerouter
	- lora
	- ssd-offload
	base_model:
	- inclusionAI/Ling-3.0-tiny-base
	pipeline_tag: text-generation
	---

	<div align="center">

	<img src="20260908-223115.jpg" alt="edge0" width="100%">

	<h1>Edge0-8b-a1b Preview</h1>

	An 8B-class sparse MoE that runs in phone-class memory.

	1 GiB active memory · 25 tok/s · 4-bit

	[![GitHub](https://img.shields.io/badge/GitHub-Edge0--AI%2Fedge0-black?style=for-the-badge&logo=github)](https://github.com/Edge0-AI/edge0)
	[![Hugging Face](https://img.shields.io/badge/%F0%9F%A4%97%20Hugging%20Face-Edge0--35b--a3b--preview-yellow?style=for-the-badge)](https://huggingface.co/Edge0/Edge0-35b-a3b-preview)
	[![Hugging Face](https://img.shields.io/badge/%F0%9F%A4%97%20Hugging%20Face-Edge0--8b--a1b--preview-yellow?style=for-the-badge)](https://huggingface.co/Edge0/Edge0-8b-a1b-preview)
	[![ModelScope](https://img.shields.io/badge/ModelScope-Edge0--35B--A3B--preview-624AFF?style=for-the-badge&logo=modelscope&logoColor=white)](https://www.modelscope.cn/models/Edge0/Edge0-35B-A3B-preview)
	[![ModelScope](https://img.shields.io/badge/ModelScope-Edge0--8B--A1B--preview-624AFF?style=for-the-badge&logo=modelscope&logoColor=white)](https://www.modelscope.cn/models/Edge0/Edge0-8B-A1B-preview)
	[![arXiv](https://img.shields.io/badge/arXiv-2609.18063-B31B1B?style=for-the-badge&logo=arxiv&logoColor=white)](https://arxiv.org/abs/2609.18063)
	[![License](https://img.shields.io/badge/License-Apache%202.0-blue?style=for-the-badge)](https://github.com/Edge0-AI/edge0/blob/main/LICENSE)

	</div>


	Edge0-8b-a1b — an 8B MoE LLM that runs at viable speed in under 1 GiB of active memory,
	via the [edge0](https://github.com/Edge0-AI/edge0) streaming inference framework.


	> Preview status: this is an early preview release of the edge0
	> pipeline. The checkpoint ships as int4 quantization plus LoRA and
	> prerouter adapters trained for this framework.

	<div align="center">

	<video
	src="https://huggingface.co/Edge0/Edge0-35B-A3B-preview/resolve/main/20260910-105854.mp4"
	controls
	playsinline
	preload="metadata"
	width="80%">
	</video>

	</div>

	## Highlights

	- Runs in phone-class memory: the full 4-bit checkpoint stays on
	storage and experts are streamed on demand, so only the active
	weights are in RAM — under 1 GiB, with no sharding and no
	upfront download of the weights into memory.
	- Fast enough for interactive use: 25 tok/s decode;
	long prompts fill in at 1400 tok/s.
	- Quality kept after quantization: Recover-LoRA distillation keeps
	the int4 model within 2.8 points of its fp16 base (and above it
	on MMLU-Pro).
	- Works out of the box: base, LoRA and prerouter adapters ship
	together and load automatically via `edge0`.


	Three mechanisms make this work:

	- SSD expert offload: expert weights are streamed from storage on
	demand — fetched only as routed, so RAM holds just the active
	weights. Peak memory is bounded by the active set, not the
	parameter count.
	- Prerouter: a trained head predicts expert routing one step
	ahead, so expert loads overlap the forward pass instead of stalling
	it — up to +59% decode throughput; the gain grows with storage
	latency, model size, and routed width K.
	- Recover-LoRA: the int4 base is frozen and LoRA adapters are
	trained by distillation from the FP teacher, recovering most of the
	quantization loss at 4-bit (see Quality below). Adapters stay
	unmerged: one read-only base serves multiple adapter sets.

	## Model summary

	\| \| \|
	\|---\|---\|
	\| Base model \| inclusionAI Ling 3.0 tiny (bailing hybrid, MLA + MoE, ≈7.9B total / ≈1.2B active) \|
	\| Quantization \| 4-bit \|
	\| Layers \| 24 \|
	\| Experts / active per token \| 128 / 8 (K=8) \|
	\| Hidden size \| 1536 \|
	\| Context \| 128k \|
	\| Thinking mode \| yes (chat template) \|
	\| License \| Apache 2.0 \|
	\| Framework \| [edge0](https://github.com/Edge0-AI/edge0) (MLX backend) \|
	\| Contents \| base checkpoint + `lora_edge0_8b.safetensors` + `prerouter_edge0_8b.safetensors` \|

	The LoRA and prerouter adapters are co-located with the base checkpoint
	and load automatically — this repository is a complete, ready-to-run
	model directory for `edge0`.

	## Quality

	All benchmarks were run by us with [OpenCompass](https://github.com/open-compass/opencompass)
	under identical settings and parameters for both models. The loss of the
	edge0 pipeline (int4 + adapters) relative to the fp16 base model is
	small: 2.8 points on average, with MMLU-Pro above the base. Max 100:

	\| Benchmark \| edge0-8b (int4) \| Ling 3.0 tiny (fp16) \|
	\|---\|---:\|---:\|
	\| AIME 2026 \| 63.3 \| 73.3 \|
	\| HumanEval \| 91.5 \| 92.7 \|
	\| GPQA-Diamond \| 70.7 \| 71.2 \|
	\| MMLU-Pro \| 70.1 \| 65.8 \|
	\| IFBench \| 53.9 \| 60.6 \|
	\| Average \| 69.9 \| 72.7 \|

	## Performance

	Measured with `examples/bench.py` on a Mac mini M4 Pro, 24 GB:

	\| Decode speed \| Prefill throughput (cold / warm) \| Peak active memory \|
	\|---\|---\|---\|
	\| 23.9–25.3 tok/s \| 500 / 1428 tok/s \| 1.0 GiB \|

	## Use cases

	- Edge / on-device inference where GPU VRAM is scarce and storage is
	fast (NVMe, internal flash).
	- Batch serving on a single commodity machine — one read-only base
	serves many LoRA adapter sets without re-quantization.
	- Multilingual chat and reasoning with thinking mode enabled by the
	bundled chat template.

	## Limitations

	- Preview release: coverage and quality are still being extended; the
	model is primarily tuned for the languages of the base model.
	- Agent capability: this preview release is not yet optimized for
	agentic tasks — tool use, multi-step planning, and long-horizon
	autonomy are currently weak. The full release will substantially
	strengthen agent capability.
	- The MLX backend currently targets Apple Silicon; other backends are
	on the edge0 roadmap.

	## Quick start

	```bash
	pip install -e 'git+https://github.com/Edge0-AI/edge0.git#egg=edge0[fetch]'

	# Download this repository into a local directory
	huggingface-cli download Edge0/Edge0-8b-a1b-preview --local-dir ./Edge0-8b-a1b-preview

	# Run it
	export EDGE0_8B_MODEL=$PWD/Edge0-8b-a1b-preview
	edge0 chat --name edge0-8b --prompt "Introduce yourself"

	# Or serve an OpenAI-compatible HTTP API
	edge0 serve --name edge0-8b --port 8083
	```

	For full usage (Python API, streaming options, prerouter details), see the
	[edge0 documentation](https://github.com/Edge0-AI/edge0#documentation).

	## License

	Apache 2.0. See [LICENSE](https://github.com/Edge0-AI/edge0/blob/main/LICENSE).

	## Citation

	If you find Edge0 useful in your research, please cite our paper:

	```bibtex
	@misc{lin2026halfmemorywallserving,
	title={The Other Half of the Memory Wall: Serving 35B MoEs from SSD with Trained Routing Prediction},
	author={Yu Lin and Yiming Wang and Runyuan Cai and Hanze Liu and Xiaodong Zeng},
	year={2026},
	eprint={2609.18063},
	archivePrefix={arXiv},
	primaryClass={cs.AI},
	url={https://arxiv.org/abs/2609.18063},
	}
	```