Instructions to use Edge0/Edge0-35B-A3B-preview with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Edge0/Edge0-35B-A3B-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/Edge0-35B-A3B-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/Edge0-35B-A3B-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/Edge0-35B-A3B-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/Edge0-35B-A3B-preview"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

MLX LM

How to use Edge0/Edge0-35B-A3B-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/Edge0-35B-A3B-preview"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "Edge0/Edge0-35B-A3B-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/Edge0-35B-A3B-preview",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

Hermes Agent

How to use Edge0/Edge0-35B-A3B-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/Edge0-35B-A3B-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/Edge0-35B-A3B-preview

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use Edge0/Edge0-35B-A3B-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/Edge0-35B-A3B-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/Edge0-35B-A3B-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"

Edge0-35B-A3B-preview / README.md

wanglamao

Update README.md

a2bf13d verified 11 days ago

3.81 kB

license: apache-2.0
library_name: mlx
tags:
  - moe
  - edge-inference
  - prerouter
  - lora
  - ssd-offload
base_model:
  - Qwen/Qwen3.5-MoE-35B-A3B
pipeline_tag: text-generation

Edge0-35b-a3b Preview

A 35B-class sparse MoE that runs on a phone — 2.9 GiB of active memory, experts streamed from SSD.

Edge0-35b-a3b — an 35B MoE LLM that runs at viable speed on portable devices in under 2.9 GiB of active memory (1/8 of its 23 GB weight footprint), via the edge0 streaming inference framework.

The key is streaming: experts are memory-mapped and fetched from SSD only as routed, so RAM holds just the active weights. What makes that viable — instead of stalling like plain parameter offloading — is a trained prerouter head that predicts the next token's expert routing one step ahead, hiding storage latency behind compute.

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.

Model summary


Base model	Qwen3.5-MoE 35B-A3B
Quantization	4-bit
Layers	40
Experts / active per token	256 / 4 (K=4)
Framework	edge0 (MLX backend)
Contents	base checkpoint + `lora_edge0_35b.safetensors` + `prerouter_edge0_35b.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 (self-evaluation)

Internal self-evaluation of this checkpoint (int4 + adapters) relative to the fp16 base model — the loss of the edge0 pipeline is small: 3.9 points on average (max 100, all self-run):

Benchmark	edge0-35b (int4)	Qwen3.5-MoE 35B-A3B (fp16)
AIME 2026	86.6	92.7
HumanEval	90.9	95.1
GPQA-Diamond	79.8	81.8
MMLU-Pro	81.0	84.6
IFBench	57.9	61.7
Average	79.2	83.2

Performance

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

Decode speed	Prefill throughput (cold / warm)	Peak active memory*
14.9–17.7 tok/s	113 / 140 tok/s	2.9 GiB

*Short contexts; long contexts add KV cache. Expert weights stream from SSD via mmap and are not resident.

Quick start

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/Edge0-35b-a3b-preview --local-dir ./Edge0-35b-a3b-preview

# Run it
export EDGE0_35B_MODEL=$PWD/Edge0-35b-a3b-preview
edge0 chat --name edge0-35b --prompt "Introduce yourself"

# Or serve an OpenAI-compatible HTTP API
edge0 serve --name edge0-35b --port 8085

For full usage (Python API, streaming options, prerouter details), see the edge0 documentation.

License

Apache 2.0. See LICENSE.