Instructions to use UnimeType/Transliteration-4B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use UnimeType/Transliteration-4B 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("UnimeType/Transliteration-4B")

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 UnimeType/Transliteration-4B with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "UnimeType/Transliteration-4B"

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": "UnimeType/Transliteration-4B"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

MLX LM

How to use UnimeType/Transliteration-4B with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "UnimeType/Transliteration-4B"

Run an OpenAI-compatible server

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

Hermes Agent

How to use UnimeType/Transliteration-4B 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 "UnimeType/Transliteration-4B"

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 UnimeType/Transliteration-4B

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use UnimeType/Transliteration-4B with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "UnimeType/Transliteration-4B"

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 "UnimeType/Transliteration-4B" \
  --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"

Transliteration-4B

File size: 1,133 Bytes

8cf5dbe

{
  "release_format": "MLX 6-bit affine, group size 64",
  "weights_unchanged_from_revision": "3e2e03c8aa8f2afffa407e90c7c2b443ecaf676f",
  "base_model": "Qwen/Qwen3.5-4B",
  "base_snapshot_revision": "not recorded in retained training configuration",
  "training_method": "LoRA on quantized 4-bit base; retained floating-point fusion followed by 6-bit quantization",
  "native_unquantized_base_precision": false,
  "retained_floating_source_sha256": {
    "model-00001-of-00002.safetensors": "5da9935a53daa73bf22809a0f89165e8d4406328ecfd6b8c3ac3f38c137c1a56",
    "model-00002-of-00002.safetensors": "01af619b9a984635330554b09cb45b652673230d55aa568a76d09449f7d066e8"
  },
  "published_model_sha256": "7d5f5d49a553d2dbeacbae56c72d69cbd3e828ee5cde4822637b1c2029fa5ac4",
  "audited_dense_tensors": 426,
  "audited_published_tensors": 924,
  "requantized_tensor_equality": true,
  "matrices_not_equal_to_sixbit_dequantization": 249,
  "training_dataset_public": false,
  "inference_hardware_verified": "Apple M5 Pro MacBook Pro, 48 GB, LM Studio MLX",
  "nvidia_cuda_inference_verified": false,
  "amd_rocm_inference_verified": false
}