Text Generation
MLX
Safetensors
English
Chinese
qwen3
oq
quantized
WebWorld
web-agent
world-model
simulator
browser
a11y
html
xml
markdown
long-horizon
long-context
synthetic-trajectories
instruction-tuning
conversational
6-bit
Instructions to use gn00029914/WebWorld-32B-oQ6 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use gn00029914/WebWorld-32B-oQ6 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("gn00029914/WebWorld-32B-oQ6") 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
- LM Studio
- Pi new
How to use gn00029914/WebWorld-32B-oQ6 with Pi:
Start the MLX server
# Install MLX LM: uv tool install mlx-lm # Start a local OpenAI-compatible server: mlx_lm.server --model "gn00029914/WebWorld-32B-oQ6"
Configure the model in Pi
# Install Pi: npm install -g @mariozechner/pi-coding-agent # Add to ~/.pi/agent/models.json: { "providers": { "mlx-lm": { "baseUrl": "http://localhost:8080/v1", "api": "openai-completions", "apiKey": "none", "models": [ { "id": "gn00029914/WebWorld-32B-oQ6" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Hermes Agent new
How to use gn00029914/WebWorld-32B-oQ6 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 "gn00029914/WebWorld-32B-oQ6"
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 gn00029914/WebWorld-32B-oQ6
Run Hermes
hermes
- MLX LM
How to use gn00029914/WebWorld-32B-oQ6 with MLX LM:
Generate or start a chat session
# Install MLX LM uv tool install mlx-lm # Interactive chat REPL mlx_lm.chat --model "gn00029914/WebWorld-32B-oQ6"
Run an OpenAI-compatible server
# Install MLX LM uv tool install mlx-lm # Start the server mlx_lm.server --model "gn00029914/WebWorld-32B-oQ6" # Calling the OpenAI-compatible server with curl curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "gn00029914/WebWorld-32B-oQ6", "messages": [ {"role": "user", "content": "Hello"} ] }'
| { | |
| "architectures": [ | |
| "Qwen3ForCausalLM" | |
| ], | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "bos_token_id": 151643, | |
| "eos_token_id": 151645, | |
| "head_dim": 128, | |
| "hidden_act": "silu", | |
| "hidden_size": 5120, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 25600, | |
| "layer_types": [ | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention" | |
| ], | |
| "max_position_embeddings": 40960, | |
| "max_window_layers": 64, | |
| "model_type": "qwen3", | |
| "num_attention_heads": 64, | |
| "num_hidden_layers": 64, | |
| "num_key_value_heads": 8, | |
| "rms_norm_eps": 1e-06, | |
| "rope_scaling": null, | |
| "rope_theta": 1000000, | |
| "sliding_window": null, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.55.0", | |
| "use_cache": false, | |
| "use_sliding_window": false, | |
| "vocab_size": 151936, | |
| "quantization": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine", | |
| "model.embed_tokens": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "model.layers.0.mlp.down_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "model.layers.0.mlp.gate_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "model.layers.0.mlp.up_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "model.layers.0.self_attn.k_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "model.layers.0.self_attn.o_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "model.layers.0.self_attn.q_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "model.layers.0.self_attn.v_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "model.layers.1.mlp.down_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "model.layers.1.self_attn.k_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "model.layers.1.self_attn.o_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "model.layers.1.self_attn.q_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "model.layers.1.self_attn.v_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "model.layers.3.self_attn.k_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "model.layers.3.self_attn.v_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "model.layers.5.self_attn.k_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "model.layers.5.self_attn.v_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "model.layers.61.self_attn.k_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "model.layers.61.self_attn.v_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "model.layers.62.mlp.down_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "model.layers.62.mlp.gate_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "model.layers.62.mlp.up_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "model.layers.62.self_attn.k_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "model.layers.62.self_attn.o_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "model.layers.62.self_attn.q_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "model.layers.62.self_attn.v_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "model.layers.63.mlp.gate_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "model.layers.63.self_attn.k_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "model.layers.63.self_attn.o_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "model.layers.63.self_attn.q_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "model.layers.63.self_attn.v_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "lm_head": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "model.layers.63.mlp.down_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "model.layers.63.mlp.up_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| } | |
| }, | |
| "quantization_config": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine", | |
| "model.embed_tokens": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "model.layers.0.mlp.down_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "model.layers.0.mlp.gate_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "model.layers.0.mlp.up_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "model.layers.0.self_attn.k_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "model.layers.0.self_attn.o_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "model.layers.0.self_attn.q_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "model.layers.0.self_attn.v_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "model.layers.1.mlp.down_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "model.layers.1.self_attn.k_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "model.layers.1.self_attn.o_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "model.layers.1.self_attn.q_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "model.layers.1.self_attn.v_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "model.layers.3.self_attn.k_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "model.layers.3.self_attn.v_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "model.layers.5.self_attn.k_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "model.layers.5.self_attn.v_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "model.layers.61.self_attn.k_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "model.layers.61.self_attn.v_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "model.layers.62.mlp.down_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "model.layers.62.mlp.gate_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "model.layers.62.mlp.up_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "model.layers.62.self_attn.k_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "model.layers.62.self_attn.o_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "model.layers.62.self_attn.q_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "model.layers.62.self_attn.v_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "model.layers.63.mlp.gate_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "model.layers.63.self_attn.k_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "model.layers.63.self_attn.o_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "model.layers.63.self_attn.q_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "model.layers.63.self_attn.v_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "lm_head": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "model.layers.63.mlp.down_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "model.layers.63.mlp.up_proj": { | |
| "bits": 8, | |
| "group_size": 64, | |
| "mode": "affine" | |
| } | |
| } | |
| } |