Instructions to use Aa09876/SmallThinker-4BA0.6B-Instruct-mlx-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Aa09876/SmallThinker-4BA0.6B-Instruct-mlx-4bit 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("Aa09876/SmallThinker-4BA0.6B-Instruct-mlx-4bit")

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 Aa09876/SmallThinker-4BA0.6B-Instruct-mlx-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 "Aa09876/SmallThinker-4BA0.6B-Instruct-mlx-4bit"

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": "Aa09876/SmallThinker-4BA0.6B-Instruct-mlx-4bit"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

OpenClaw new

How to use Aa09876/SmallThinker-4BA0.6B-Instruct-mlx-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 "Aa09876/SmallThinker-4BA0.6B-Instruct-mlx-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 "Aa09876/SmallThinker-4BA0.6B-Instruct-mlx-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"

MLX LM

How to use Aa09876/SmallThinker-4BA0.6B-Instruct-mlx-4bit with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "Aa09876/SmallThinker-4BA0.6B-Instruct-mlx-4bit"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "Aa09876/SmallThinker-4BA0.6B-Instruct-mlx-4bit"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "Aa09876/SmallThinker-4BA0.6B-Instruct-mlx-4bit",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

Hermes Agent

How to use Aa09876/SmallThinker-4BA0.6B-Instruct-mlx-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 "Aa09876/SmallThinker-4BA0.6B-Instruct-mlx-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 Aa09876/SmallThinker-4BA0.6B-Instruct-mlx-4bit

Run Hermes

hermes

SmallThinker-4BA0.6B-Instruct-mlx-4bit / config.json

Aa09876

Add MLX 4-bit conversion of SmallThinker-4BA0.6B-Instruct (+ mlx_lm arch module)

6efa8bf verified 15 days ago

Raw

History Blame Contribute Delete

2.27 kB

	{
	"architectures": [
	"SmallThinkerForCausalLM"
	],
	"attention_dropout": 0.0,
	"auto_map": {
	"AutoConfig": "configuration_smallthinker.SmallThinkerConfig",
	"AutoModel": "modeling_smallthinker.SmallThinkerForCausalLM",
	"AutoModelForCausalLM": "modeling_smallthinker.SmallThinkerForCausalLM"
	},
	"bos_token_id": 151643,
	"eos_token_id": [
	151643,
	151645
	],
	"head_dim": 128,
	"hidden_size": 1536,
	"initializer_range": 0.02,
	"max_length": null,
	"max_position_embeddings": 32768,
	"model_name": "smallthinker_4b_instruct",
	"model_type": "smallthinker",
	"moe_ffn_hidden_size": 768,
	"moe_num_active_primary_experts": 4,
	"moe_num_primary_experts": 32,
	"norm_topk_prob": true,
	"num_attention_heads": 12,
	"num_hidden_layers": 32,
	"num_key_value_heads": 2,
	"output_router_logits": false,
	"quantization": {
	"group_size": 64,
	"bits": 4,
	"mode": "affine"
	},
	"quantization_config": {
	"group_size": 64,
	"bits": 4,
	"mode": "affine"
	},
	"repetition_penalty": null,
	"rms_norm_eps": 1e-06,
	"rope_layout": [
	1,
	1,
	1,
	1,
	1,
	1,
	1,
	1,
	1,
	1,
	1,
	1,
	1,
	1,
	1,
	1,
	1,
	1,
	1,
	1,
	1,
	1,
	1,
	1,
	1,
	1,
	1,
	1,
	1,
	1,
	1,
	1
	],
	"rope_scaling": null,
	"rope_theta": 1500000.0,
	"sliding_window_layout": [
	0,
	0,
	0,
	0,
	0,
	0,
	0,
	0,
	0,
	0,
	0,
	0,
	0,
	0,
	0,
	0,
	0,
	0,
	0,
	0,
	0,
	0,
	0,
	0,
	0,
	0,
	0,
	0,
	0,
	0,
	0,
	0
	],
	"sliding_window_size": 4096,
	"temperature": null,
	"tie_word_embeddings": true,
	"tokenizer_class": "Qwen2Tokenizer",
	"top_p": null,
	"torch_dtype": "bfloat16",
	"transformers_version": "4.53.3",
	"use_cache": false,
	"vocab_size": 151936
	}