Instructions to use mlx-community/Inkling-2-Small-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use mlx-community/Inkling-2-Small-4bit 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("mlx-community/Inkling-2-Small-4bit") config = load_config("mlx-community/Inkling-2-Small-4bit") # 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
- Pi
How to use mlx-community/Inkling-2-Small-4bit with Pi:
Start the MLX server
# Install MLX LM: uv tool install mlx-lm # Start a local OpenAI-compatible server: mlx_lm.server --model "mlx-community/Inkling-2-Small-4bit"
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": "mlx-community/Inkling-2-Small-4bit" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Hermes Agent
How to use mlx-community/Inkling-2-Small-4bit 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 "mlx-community/Inkling-2-Small-4bit"
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 mlx-community/Inkling-2-Small-4bit
Run Hermes
hermes
- Atomic Chat
- OpenClaw
How to use mlx-community/Inkling-2-Small-4bit with OpenClaw:
Start the MLX server
# Install MLX LM: uv tool install mlx-lm # Start a local OpenAI-compatible server: mlx_lm.server --model "mlx-community/Inkling-2-Small-4bit"
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 "mlx-community/Inkling-2-Small-4bit" \ --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"
Download config.json from mlx-community/Inkling-2-Small-4bit: direct link, hf CLI and curl.
- Browser
- Download file 3.5 kB
-
https://huggingface.co/mlx-community/Inkling-2-Small-4bit/resolve/main/config.json
- Command line
-
hf download hf://mlx-community/Inkling-2-Small-4bit/config.json
-
curl -L -o config.json https://huggingface.co/mlx-community/Inkling-2-Small-4bit/resolve/main/config.json
3.5 kB
| { | |
| "architectures": [ | |
| "Inkling2ForConditionalGeneration" | |
| ], | |
| "eos_token_id": 200006, | |
| "model_type": "inkling2", | |
| "mtp_config": { | |
| "hidden_size": 4608, | |
| "num_hidden_layers": 5, | |
| "num_attention_heads": 48, | |
| "num_key_value_heads": 8, | |
| "head_dim": 128, | |
| "intermediate_size": 18432, | |
| "max_position_embeddings": 1048576, | |
| "torch_dtype": "bfloat16", | |
| "q_bias": false, | |
| "o_bias": false, | |
| "rms_norm_eps": 1e-06, | |
| "rope_theta": 1000000.0, | |
| "local_layer_ids": [ | |
| 0, | |
| 1, | |
| 3, | |
| 4 | |
| ], | |
| "sliding_window_size": 1024, | |
| "block_size": 8, | |
| "markov_rank": 256, | |
| "markov_head_type": "rnn_hidden", | |
| "target_layer_ids": [ | |
| 5, | |
| 11, | |
| 17, | |
| 23, | |
| 29, | |
| 35, | |
| 41, | |
| 48 | |
| ] | |
| }, | |
| "quantization": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "quantization_config": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "text_config": { | |
| "model_max_length": 1048576, | |
| "torch_dtype": "bfloat16", | |
| "hidden_size": 4608, | |
| "num_hidden_layers": 48, | |
| "vocab_size": 201024, | |
| "num_attention_heads": 48, | |
| "num_key_value_heads": 8, | |
| "head_dim": 128, | |
| "d_rel": 16, | |
| "rel_extent": 1024, | |
| "q_bias": false, | |
| "o_bias": false, | |
| "log_scaling_n_floor": 128000, | |
| "log_scaling_alpha": 0.1, | |
| "rms_norm_eps": 1e-06, | |
| "pre_norm_pre_affine": false, | |
| "final_norm_pre_affine": false, | |
| "use_value_norm_no_gamma": true, | |
| "qk_l2_clip_threshold": 22.627416997969522, | |
| "rel_l2_clip_threshold": 8.0, | |
| "local_layer_ids": [ | |
| 0, | |
| 1, | |
| 2, | |
| 3, | |
| 4, | |
| 6, | |
| 7, | |
| 8, | |
| 9, | |
| 10, | |
| 12, | |
| 13, | |
| 14, | |
| 15, | |
| 16, | |
| 18, | |
| 19, | |
| 20, | |
| 21, | |
| 22, | |
| 24, | |
| 25, | |
| 26, | |
| 27, | |
| 28, | |
| 30, | |
| 31, | |
| 32, | |
| 33, | |
| 34, | |
| 36, | |
| 37, | |
| 38, | |
| 39, | |
| 40, | |
| 42, | |
| 43, | |
| 44, | |
| 45, | |
| 46 | |
| ], | |
| "sconv_kernel_size": 4, | |
| "unpadded_vocab_size": 200058, | |
| "final_logit_softcapping": 30.0, | |
| "swa_head_dim": 128, | |
| "swa_num_attention_heads": 48, | |
| "swa_num_key_value_heads": 8, | |
| "sliding_window_size": 1024, | |
| "n_layers_per_attn_res_block": 6, | |
| "attn_res_normalize_values": true, | |
| "n_routed_experts": 384, | |
| "num_experts_per_tok": 8, | |
| "n_shared_experts": 0, | |
| "intermediate_size": 2304, | |
| "mlp_gate_softcap": 4.0, | |
| "mlp_up_softcap": 25.0, | |
| "route_scale": 8.0, | |
| "use_gate_bias": true | |
| }, | |
| "vision_config": { | |
| "temporal_patch_size": 2, | |
| "native_patch_size": 20, | |
| "adapter_merge_size": 2, | |
| "projection_hidden_dim": 4096, | |
| "projector_bias": false, | |
| "hidden_size": 1024, | |
| "num_hidden_layers": 23, | |
| "num_attention_heads": 16, | |
| "mlp_ratio": 4.0, | |
| "posemb_grid_size": 32, | |
| "layer_norm_eps": 1e-05 | |
| } | |
| } |