Instructions to use krzonkalla/test-quant-mlx-rio-mini with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use krzonkalla/test-quant-mlx-rio-mini 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("krzonkalla/test-quant-mlx-rio-mini") config = load_config("krzonkalla/test-quant-mlx-rio-mini") # 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
- LM Studio
- Pi new
How to use krzonkalla/test-quant-mlx-rio-mini with Pi:
Start the MLX server
# Install MLX LM: uv tool install mlx-lm # Start a local OpenAI-compatible server: mlx_lm.server --model "krzonkalla/test-quant-mlx-rio-mini"
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": "krzonkalla/test-quant-mlx-rio-mini" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Hermes Agent new
How to use krzonkalla/test-quant-mlx-rio-mini 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 "krzonkalla/test-quant-mlx-rio-mini"
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 krzonkalla/test-quant-mlx-rio-mini
Run Hermes
hermes
| { | |
| "architectures": [ | |
| "Qwen3_5MoeForConditionalGeneration" | |
| ], | |
| "eos_token_id": [ | |
| 248046, | |
| 248044 | |
| ], | |
| "image_token_id": 248056, | |
| "model_type": "qwen3_5_moe", | |
| "quantization": { | |
| "group_size": 64, | |
| "bits": 3, | |
| "mode": "affine" | |
| }, | |
| "quantization_config": { | |
| "group_size": 64, | |
| "bits": 3, | |
| "mode": "affine" | |
| }, | |
| "text_config": { | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "attn_output_gate": true, | |
| "dtype": "bfloat16", | |
| "eos_token_id": 248044, | |
| "full_attention_interval": 4, | |
| "head_dim": 256, | |
| "hidden_act": "silu", | |
| "hidden_size": 2048, | |
| "initializer_range": 0.02, | |
| "layer_types": [ | |
| "linear_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "full_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "full_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "full_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "full_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "full_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "full_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "full_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "full_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "full_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "full_attention" | |
| ], | |
| "linear_conv_kernel_dim": 4, | |
| "linear_key_head_dim": 128, | |
| "linear_num_key_heads": 16, | |
| "linear_num_value_heads": 32, | |
| "linear_value_head_dim": 128, | |
| "max_position_embeddings": 262144, | |
| "mlp_only_layers": [], | |
| "model_type": "qwen3_5_moe_text", | |
| "moe_intermediate_size": 512, | |
| "mtp_num_hidden_layers": 1, | |
| "mtp_use_dedicated_embeddings": false, | |
| "num_attention_heads": 16, | |
| "num_experts": 256, | |
| "num_experts_per_tok": 8, | |
| "num_hidden_layers": 40, | |
| "num_key_value_heads": 2, | |
| "rms_norm_eps": 1e-06, | |
| "router_aux_loss_coef": 0.001, | |
| "shared_expert_intermediate_size": 512, | |
| "use_cache": true, | |
| "vocab_size": 248320, | |
| "mamba_ssm_dtype": "float32", | |
| "rope_parameters": { | |
| "mrope_interleaved": true, | |
| "mrope_section": [ | |
| 11, | |
| 11, | |
| 10 | |
| ], | |
| "rope_type": "default", | |
| "rope_theta": 10000000, | |
| "partial_rotary_factor": 0.25 | |
| } | |
| }, | |
| "tie_word_embeddings": false, | |
| "transformers_version": "4.57.0.dev0", | |
| "video_token_id": 248057, | |
| "vision_config": { | |
| "deepstack_visual_indexes": [], | |
| "depth": 27, | |
| "hidden_act": "gelu_pytorch_tanh", | |
| "hidden_size": 1152, | |
| "in_channels": 3, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 4304, | |
| "model_type": "qwen3_5_moe", | |
| "num_heads": 16, | |
| "num_position_embeddings": 2304, | |
| "out_hidden_size": 2048, | |
| "patch_size": 16, | |
| "spatial_merge_size": 2, | |
| "temporal_patch_size": 2 | |
| }, | |
| "vision_end_token_id": 248054, | |
| "vision_start_token_id": 248053 | |
| } |