Instructions to use huyxdang/text-gpt-live with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use huyxdang/text-gpt-live 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("huyxdang/text-gpt-live")

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 huyxdang/text-gpt-live with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "huyxdang/text-gpt-live"

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": "huyxdang/text-gpt-live"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

OpenClaw new

How to use huyxdang/text-gpt-live with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "huyxdang/text-gpt-live"

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 "huyxdang/text-gpt-live" \
  --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 huyxdang/text-gpt-live with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "huyxdang/text-gpt-live"

Run an OpenAI-compatible server

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

Hermes Agent

How to use huyxdang/text-gpt-live 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 "huyxdang/text-gpt-live"

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 huyxdang/text-gpt-live

Run Hermes

hermes

Text GPT-Live

Text GPT-Live is an 8-bit MLX checkpoint for a small text interaction model. It continuously evaluates a stream of typed-text snapshots and emits a single next interaction action: stay silent, respond, highlight, suggest an edit, commit a translation unit, start a web search, or delegate background work.

Base model and training

Base: Qwen/Qwen3.5-4B
Fine-tuning: supervised LoRA, merged into the released checkpoint
Main g1-v2 stage: 2,903 synthetic decision cards, one epoch
Delivery-repair continuation: 544 cards, one epoch
Deployment format: 8-bit MLX affine quantization (group size 64)

The release uses the selected fixed-index delivery repair. It was chosen because the 4-bit candidate changed a required search-result target index in local acceptance, while this 8-bit checkpoint preserved the selected model output.

Behavior and limitations

The model was evaluated on synthetic event streams and local closed-loop demos for dialog/silence, simple highlighting, incremental Chinese translation, and concurrent delegation plus web-search delivery. Demo 5 (time awareness) is not included. This checkpoint is a research/demo artifact, not a general assistant.

Its selected local persistent-cache benchmark measured 971.55 ms median and 1,128.68 ms p95 per model decision; it does not meet the project's 650 ms target. Simple highlighting is also not robust on longer streams, and translation quality remains a known limitation.

Files

model.safetensors is the complete merged 8-bit MLX checkpoint. The repository also includes the selected source LoRA adapter (adapter_model.safetensors and adapter_config.json), so the merge can be reproduced from Qwen/Qwen3.5-4B. MERGE_PROVENANCE.json records the selected merge settings.

Training data

The two selected training stages are published at huyxdang/text-gpt-live-dataset.

License

This release follows the licensing and use terms of its Qwen base model. Review the base model's license before use or redistribution.

Downloads last month: 55

Safetensors

Model size

1B params

Tensor type

BF16

U32

F32

MLX

Hardware compatibility

8-bit