Text Generation
MLX
Safetensors
English
qwen3
transcription
text-cleanup
4bit
quantized
apple-silicon
conversational
Eval Results (legacy)
4-bit precision
Instructions to use shantanugoel/aawaaz-qwen3-0.6b-transcriber-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use shantanugoel/aawaaz-qwen3-0.6b-transcriber-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("shantanugoel/aawaaz-qwen3-0.6b-transcriber-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 shantanugoel/aawaaz-qwen3-0.6b-transcriber-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 "shantanugoel/aawaaz-qwen3-0.6b-transcriber-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": "shantanugoel/aawaaz-qwen3-0.6b-transcriber-4bit" } ] } } }Run Pi
# Start Pi in your project directory: pi
- MLX LM
How to use shantanugoel/aawaaz-qwen3-0.6b-transcriber-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 "shantanugoel/aawaaz-qwen3-0.6b-transcriber-4bit"
Run an OpenAI-compatible server
# Install MLX LM uv tool install mlx-lm # Start the server mlx_lm.server --model "shantanugoel/aawaaz-qwen3-0.6b-transcriber-4bit" # Calling the OpenAI-compatible server with curl curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "shantanugoel/aawaaz-qwen3-0.6b-transcriber-4bit", "messages": [ {"role": "user", "content": "Hello"} ] }' - Hermes Agent
How to use shantanugoel/aawaaz-qwen3-0.6b-transcriber-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 "shantanugoel/aawaaz-qwen3-0.6b-transcriber-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 shantanugoel/aawaaz-qwen3-0.6b-transcriber-4bit
Run Hermes
hermes
- Atomic Chat
- OpenClaw
How to use shantanugoel/aawaaz-qwen3-0.6b-transcriber-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 "shantanugoel/aawaaz-qwen3-0.6b-transcriber-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 "shantanugoel/aawaaz-qwen3-0.6b-transcriber-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"
Strip local filesystem paths from quantize_summary.json
Browse files- quantize_summary.json +4 -4
quantize_summary.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
"status": "completed",
|
| 3 |
"model": "qwen3-0.6b",
|
| 4 |
-
"source_dir": "
|
| 5 |
-
"output_dir": "
|
| 6 |
"bits": 4,
|
| 7 |
"group_size": 64,
|
| 8 |
"source_size_mb": 1147.8,
|
|
@@ -17,7 +17,7 @@
|
|
| 17 |
"outputs": [
|
| 18 |
"Pesto from scratch:\n- 2 cups fresh basil, packed tight\n- 1/3 cup pine nuts\n- 2 cloves garlic\n- 1/2 cup Parmesan, grated\n- 1/2 cup olive oil\n\nInstructions:\n1. Hit the food processor with some salt and lemon juice (half a lemon makes it pop).",
|
| 19 |
"Dear Tenant,\n\nThis letter serves as official notice that your monthly rent will increase from $1,450 to $1,525 effective April 1, 2025. This represents a 5.2% increase.\n\nIf you wish to continue your tenancy under these new terms, please sign and return the attached lease amendment by March 1.\n\nIf we don't hear from you by then, we'll assume you'll be vacating at the end of your current lease period.\n\nSincerely,\nMaple Grove Property Management",
|
| 20 |
-
"Meeting Notes
|
| 21 |
"For the science education study, we used a randomized controlled design with 832 high school students in 16 classrooms. Compared traditional lecture-based instruction to argument-driven inquiry, the treatment group showed significantly greater gains on the test of scientific argumentation. The effect size was about 0.67, and importantly, the gains were largest for students who started with lower baseline scores, suggesting it helps close achievement gaps.",
|
| 22 |
"I tried making a terrarium. It's a glass container with plants inside. It creates its own ecosystem. Start with pebbles for drainage, activated charcoal to keep it fresh, soil, plants. Used a large glass jar that used to have pickles in it. Put in tiny ferns, moss, and a small piece of driftwood. Sealed the lid. First week it fogged up inside, which means it's creating its own water cycle. The moisture evaporates from the soil, condenses on the glass, drips back down like rain in a jar. Haven't "
|
| 23 |
]
|
|
@@ -30,4 +30,4 @@
|
|
| 30 |
"degradation_signals": []
|
| 31 |
}
|
| 32 |
}
|
| 33 |
-
}
|
|
|
|
| 1 |
{
|
| 2 |
"status": "completed",
|
| 3 |
"model": "qwen3-0.6b",
|
| 4 |
+
"source_dir": "qwen3-0.6b",
|
| 5 |
+
"output_dir": "qwen3-0.6b-4bit",
|
| 6 |
"bits": 4,
|
| 7 |
"group_size": 64,
|
| 8 |
"source_size_mb": 1147.8,
|
|
|
|
| 17 |
"outputs": [
|
| 18 |
"Pesto from scratch:\n- 2 cups fresh basil, packed tight\n- 1/3 cup pine nuts\n- 2 cloves garlic\n- 1/2 cup Parmesan, grated\n- 1/2 cup olive oil\n\nInstructions:\n1. Hit the food processor with some salt and lemon juice (half a lemon makes it pop).",
|
| 19 |
"Dear Tenant,\n\nThis letter serves as official notice that your monthly rent will increase from $1,450 to $1,525 effective April 1, 2025. This represents a 5.2% increase.\n\nIf you wish to continue your tenancy under these new terms, please sign and return the attached lease amendment by March 1.\n\nIf we don't hear from you by then, we'll assume you'll be vacating at the end of your current lease period.\n\nSincerely,\nMaple Grove Property Management",
|
| 20 |
+
"Meeting Notes — Cloud Migration Standup, December 9, 2026\n\nAttendees: Victor Chang, Priya Subramanian, and myself.\n\n**Workload Distribution**\nVictor said we've moved about 60% of the workloads to AWS, so far which puts us a little behind the 70% target for end of November. But he said the delay was mostly because the compliance team took an extra two weeks to approve the data residency stuff for the EU region.\n\n**Networking Costs**\nPriya said the networking costs are already 30% higher than the ",
|
| 21 |
"For the science education study, we used a randomized controlled design with 832 high school students in 16 classrooms. Compared traditional lecture-based instruction to argument-driven inquiry, the treatment group showed significantly greater gains on the test of scientific argumentation. The effect size was about 0.67, and importantly, the gains were largest for students who started with lower baseline scores, suggesting it helps close achievement gaps.",
|
| 22 |
"I tried making a terrarium. It's a glass container with plants inside. It creates its own ecosystem. Start with pebbles for drainage, activated charcoal to keep it fresh, soil, plants. Used a large glass jar that used to have pickles in it. Put in tiny ferns, moss, and a small piece of driftwood. Sealed the lid. First week it fogged up inside, which means it's creating its own water cycle. The moisture evaporates from the soil, condenses on the glass, drips back down like rain in a jar. Haven't "
|
| 23 |
]
|
|
|
|
| 30 |
"degradation_signals": []
|
| 31 |
}
|
| 32 |
}
|
| 33 |
+
}
|