Text Generation
MLX
Safetensors
spark2_5
spark-x2.5
long-context
1m-context
conversational
custom_code
4-bit precision
Instructions to use abenzerps/Spark-X2.5-4B-MLX-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use abenzerps/Spark-X2.5-4B-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("abenzerps/Spark-X2.5-4B-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
- Pi
How to use abenzerps/Spark-X2.5-4B-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 "abenzerps/Spark-X2.5-4B-MLX-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": "abenzerps/Spark-X2.5-4B-MLX-4bit" } ] } } }Run Pi
# Start Pi in your project directory: pi
- MLX LM
How to use abenzerps/Spark-X2.5-4B-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 "abenzerps/Spark-X2.5-4B-MLX-4bit"
Run an OpenAI-compatible server
# Install MLX LM uv tool install mlx-lm # Start the server mlx_lm.server --model "abenzerps/Spark-X2.5-4B-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": "abenzerps/Spark-X2.5-4B-MLX-4bit", "messages": [ {"role": "user", "content": "Hello"} ] }' - Hermes Agent
How to use abenzerps/Spark-X2.5-4B-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 "abenzerps/Spark-X2.5-4B-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 abenzerps/Spark-X2.5-4B-MLX-4bit
Run Hermes
hermes
- Atomic Chat
- OpenClaw
How to use abenzerps/Spark-X2.5-4B-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 "abenzerps/Spark-X2.5-4B-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 "abenzerps/Spark-X2.5-4B-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"
| {#- 0826版本 -#} | |
| {%- if not messages %} | |
| {{- raise_exception('No messages provided.') }} | |
| {%- endif %} | |
| {%- set enable_thinking = enable_thinking | default(true) %} | |
| {#- Render a string or a list of text blocks. -#} | |
| {%- macro render_content(content, context_name) %} | |
| {%- if content is string %} | |
| {{- content }} | |
| {%- elif content is none or content is undefined %} | |
| {{- '' }} | |
| {%- elif content is iterable and content is not mapping %} | |
| {%- for block in content %} | |
| {%- if block.type == 'text' %} | |
| {{- block.text }} | |
| {%- else %} | |
| {{- raise_exception('Unsupported ' ~ context_name ~ ' content block type: ' ~ (block.type | string)) }} | |
| {%- endif %} | |
| {%- endfor %} | |
| {%- else %} | |
| {{- raise_exception(context_name ~ ' content must be a string or a list of text blocks') }} | |
| {%- endif %} | |
| {%- endmacro %} | |
| {#- Default system prompt -#} | |
| {%- set default_system = "you are a helpful assistant." %} | |
| {#- The first message-level system is placed in the initial system block. -#} | |
| {%- set ns = namespace(initial_system='') %} | |
| {%- if messages[0].role == "system" %} | |
| {%- set ns.initial_system = render_content(messages[0].content, 'system') %} | |
| {%- endif %} | |
| {#- System block -#} | |
| {{- '<|start▁of▁sentence|><|System|>' + '\n' + default_system }} | |
| {%- if tools %} | |
| {{- '## Tools' + '\n' + 'You have access to the following functions:' + '\n' + '<tools>' }} | |
| {%- for tool in tools %} | |
| {{- '\n' + tool.function | tojson}} | |
| {%- endfor %} | |
| {{- '\n' + '</tools>' }} | |
| {%- endif %} | |
| {%- if ns.initial_system %} | |
| {{- '\n\n' + ns.initial_system }} | |
| {%- endif %} | |
| {{- '<|end▁of▁sentence|>'}} | |
| {#- Conversation turns -#} | |
| {%- for message in messages %} | |
| {%- if message.role == "system" %} | |
| {#- The first system message was consumed by the initial block. -#} | |
| {%- if not loop.first %} | |
| {{- '<|start▁of▁sentence|><|System|>\n' + render_content(message.content, 'system') + '<|end▁of▁sentence|>' }} | |
| {%- endif %} | |
| {%- elif message.role == "user" %} | |
| {{- '<|start▁of▁sentence|><|User|>' + render_content(message.content, 'user') + '<|end▁of▁sentence|>' }} | |
| {%- elif message.role == "assistant" %} | |
| {%- set assistant_content = render_content(message.content, 'assistant') %} | |
| {%- if message.reasoning_content is defined and message.reasoning_content %} | |
| {%- set reasoning_content = message.reasoning_content %} | |
| {%- else %} | |
| {%- set reasoning_content = '' %} | |
| {%- endif %} | |
| {{- '<|start▁of▁sentence|><|Bot|>'}} | |
| {%- if reasoning_content %} | |
| {{- '<think>' + reasoning_content + '</think>'}} | |
| {%- else %} | |
| {{- '</think>' }} | |
| {%- endif %} | |
| {%- if assistant_content %} | |
| {{- assistant_content }} | |
| {%- endif %} | |
| {%- if message.tool_calls is defined and message.tool_calls is not none %} | |
| {%- for tool_call in message.tool_calls %} | |
| {%- if tool_call.function.arguments is not mapping %} | |
| {{- raise_exception('tool_call.function.arguments must be a dictionary; normalize JSON strings before apply_chat_template') }} | |
| {%- endif %} | |
| {%- set args = tool_call.function.arguments %} | |
| {{- '<tool_call>' + tool_call.function.name }} | |
| {%- for k, v in args.items() %} | |
| {{- '<arg_key>' ~ k ~ '</arg_key><arg_value>' ~ (v if v is string else v | tojson) ~ '</arg_value>' }} | |
| {%- endfor %} | |
| {{- '</tool_call>' }} | |
| {%- endfor %} | |
| {%- endif %} | |
| {{- '<|end▁of▁sentence|>' }} | |
| {%- elif message.role == "tool" %} | |
| {%- if loop.previtem is undefined or loop.previtem.role != "tool" %} | |
| {{- '<|start▁of▁sentence|><|Tool|>' }} | |
| {%- endif %} | |
| {{- '<tool_response>' ~ message.content ~ '</tool_response>' }} | |
| {%- if loop.nextitem is undefined or loop.nextitem.role != "tool" %} | |
| {{- '<|end▁of▁sentence|>' }} | |
| {%- endif %} | |
| {%- else %} | |
| {{- raise_exception('Unsupported message role: ' ~ message.role) }} | |
| {%- endif %} | |
| {%- endfor %} | |
| {#- Generation prompt -#} | |
| {%- if add_generation_prompt %} | |
| {{- '<|start▁of▁sentence|><|Bot|>' }} | |
| {%- if enable_thinking is defined and enable_thinking %} | |
| {{- '<think>' }} | |
| {%- endif %} | |
| {%- if enable_thinking is defined and not enable_thinking %} | |
| {{- '</think>' }} | |
| {%- endif %} | |
| {%- endif %} | |