Instructions to use OsaurusAI/Qwen3.5-35B-A3B-JANG_4K with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use OsaurusAI/Qwen3.5-35B-A3B-JANG_4K with MLX:

# Make sure mlx-vlm is installed
# pip install --upgrade mlx-vlm

from mlx_vlm import load, generate
from mlx_vlm.prompt_utils import apply_chat_template
from mlx_vlm.utils import load_config

# Load the model
model, processor = load("OsaurusAI/Qwen3.5-35B-A3B-JANG_4K")
config = load_config("OsaurusAI/Qwen3.5-35B-A3B-JANG_4K")

# Prepare input
image = ["http://images.cocodataset.org/val2017/000000039769.jpg"]
prompt = "Describe this image."

# Apply chat template
formatted_prompt = apply_chat_template(
    processor, config, prompt, num_images=1
)

# Generate output
output = generate(model, processor, formatted_prompt, image)
print(output)

Notebooks
Google Colab
Kaggle
Local Apps Settings
LM Studio

How to use OsaurusAI/Qwen3.5-35B-A3B-JANG_4K with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "OsaurusAI/Qwen3.5-35B-A3B-JANG_4K"

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": "OsaurusAI/Qwen3.5-35B-A3B-JANG_4K"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent

How to use OsaurusAI/Qwen3.5-35B-A3B-JANG_4K 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 "OsaurusAI/Qwen3.5-35B-A3B-JANG_4K"

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 OsaurusAI/Qwen3.5-35B-A3B-JANG_4K

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use OsaurusAI/Qwen3.5-35B-A3B-JANG_4K with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "OsaurusAI/Qwen3.5-35B-A3B-JANG_4K"

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 "OsaurusAI/Qwen3.5-35B-A3B-JANG_4K" \
  --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"

Qwen 3.5 35B-A3B — JANG_4K (Mixed-Precision, 4-bit)

JANG — Jang Adaptive N-bit Grading | Mixed-Precision Quantization for Apple Silicon

Osaurus natively supports JANG models. Download at osaurus.ai.

Model Details

Property	Value
Base Model	Qwen 3.5 VL 35B-A3B
Architecture	MoE Transformer + Vision
Total Parameters	35B (3B active per token)
Profile	JANG_4K
Avg Bits/Weight	3.98
Bit Widths Used	3, 4, 5, 8
Model Size	16.4 GB
Vision	Yes
Format	JANG v2 (MLX-native safetensors)

Benchmarks

200-question MMLU (20 per subject x 10 subjects). Thinking OFF (enable_thinking=False), greedy decoding (temp=0.0).

Model	MMLU	Size
JANG_4K (this)	77.5%	16.4 GB
MLX 4-bit	75.5%	18 GB
MLX 2-bit	~20%	10 GB

JANG_4K beats MLX 4-bit by +2 MMLU while being smaller (16.4 GB vs 18 GB). Budget-neutral bit redistribution boosts attention quality without increasing total size.

JANG_4K Profile

JANG_4K is a balanced 4-bit mixed-precision profile that provides near-original quality. Critical layers (attention, routing, embeddings) are kept at 8-bit, with expert MLP weights at 3-5 bit depending on importance scoring. Best quality-to-size ratio for most use cases.

Usage

# Requires Osaurus (https://osaurus.ai)
osaurus serve OsaurusAI/Qwen3.5-35B-A3B-JANG_4K

Requirements

Apple Silicon Mac with 24+ GB unified memory
MLX framework with Qwen 3.5 MoE support

Quantized by Osaurus AI using JANG

Downloads last month: 16

Safetensors

Model size

47B params

Tensor type

U32

F16

MLX

Hardware compatibility

Quantized