Instructions to use imYChaudhary22/zen-polish-v3-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use imYChaudhary22/zen-polish-v3-4bit 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("imYChaudhary22/zen-polish-v3-4bit")

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 imYChaudhary22/zen-polish-v3-4bit with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "imYChaudhary22/zen-polish-v3-4bit"

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": "imYChaudhary22/zen-polish-v3-4bit"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

MLX LM

How to use imYChaudhary22/zen-polish-v3-4bit with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "imYChaudhary22/zen-polish-v3-4bit"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "imYChaudhary22/zen-polish-v3-4bit"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "imYChaudhary22/zen-polish-v3-4bit",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

Hermes Agent

How to use imYChaudhary22/zen-polish-v3-4bit 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 "imYChaudhary22/zen-polish-v3-4bit"

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 imYChaudhary22/zen-polish-v3-4bit

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use imYChaudhary22/zen-polish-v3-4bit with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "imYChaudhary22/zen-polish-v3-4bit"

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 "imYChaudhary22/zen-polish-v3-4bit" \
  --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"

ZenPolish v3 (4B)

ZenVoice's on-device dictation-enhancement model. Takes the raw, unpunctuated text produced by speech-to-text engines and restores everything dictation loses: punctuation, capitalization, filler removal, spoken numbers, dates, and times. Runs fully on-device on Apple Silicon via MLX — nothing leaves the Mac.

Base model: fine-tuned (LoRA rank 16) from Qwen3-4B-Instruct-2507, then merged in 4-bit MLX. Qwen3 is the starting point; the formatting behavior below is entirely the fine-tune.

Usage

ChatML prompt, thinking disabled:

messages = [
    {"role": "system", "content": SYSTEM_PROMPT},
    {"role": "user", "content": "um yeah so we need to fix this bug by tuesday right check the pull request"},
]
# -> "Um, yeah, so we need to fix this bug by Tuesday. Check the pull request."

The exact system prompt is in the ZenVoice repository (training/common.py).

Evaluation

Measured on ZenVoice's leakage-controlled 234-row eval suite (training/evaluate_v31.py over training/data/eval_v31.jsonl: 7 speech categories, rows appearing in any training mix excluded, ITN values disjoint from training templates), greedy decoding.

Metric	ZenPolish v3 (4B)	ZenPolish v2 (1.7B)	Stock Qwen3-4B	Raw input floor
WER	17.2%	30.5%	24.4%	40.4%
Exact match	41.0%	23.1%	33.3%	0.0%
Punctuation F1	0.750	0.649	0.745	0.000
New-content (hallucination) rate	10.8%	23.0%	17.1%	32.5%
Capitalization accuracy	95.6%	92.4%	95.4%	76.5%
Sentence-start accuracy	80.7%	62.1%	73.9%	0.9%

Per-category WER highlights (v3 vs v2): numbers/dates/money ITN 13.8% vs 37.3%, heavy filler/restart speech 31.8% vs 78.6%, run-on speech 14.4% vs 14.6%, questions 4.9% vs 0.6%.

Scope

English-focused
Formatting and cleanup only — never rewrites meaning, never adds content
Strengths: punctuation, casing, filler/restart removal, spoken money and clock times, dates, percents
Weak spots: over-cleanup on 1-5-word fragments; filler removal on very dense speech is improved but not solved

Training

Pipeline and recipe are in the ZenVoice repo under training/: build_pairs_v31.py (teacher pairs, filler/restart-intensity branch, ITN hard cases), noisifier, synthetic + real ASR pair builders, frozen eval sets, mlx-lm LoRA training (rank 16, ~25k pairs), and the WER no-regression gate. Weights: 4-bit MLX safetensors, 2.1 GB.

License

Apache-2.0, inherited from the Qwen3-4B base.

Downloads last month: 33

Safetensors

Model size

4B params

Tensor type

U32

BF16

MLX

Hardware compatibility

4-bit

Model tree for imYChaudhary22/zen-polish-v3-4bit

Base model

Qwen/Qwen3-4B-Instruct-2507

Quantized

mlx-community/Qwen3-4B-Instruct-2507-4bit

Quantized

(4)

this model