---
language:
- en
- zh
license: apache-2.0
library_name: aria-engine
tags:
- qwen3
- quantized
- group-quantization
- hadamard
- lloyd-max
- 4-bit
- on-device
- edge
- mobile
- text-generation
- tool-calling
- embeddings
pipeline_tag: text-generation
datasets:
- togethercomputer/RedPajama-Data-1T
- EleutherAI/the_pile
- bigcode/the-stack
base_model: Qwen/Qwen3-0.6B
model-index:
- name: Qwen3-0.6B (Aria Quant Bundle, q4)
  results:
  - task:
      type: text-generation
      name: Generation Consistency (vs FP16)
    metrics:
    - type: mean_token_overlap
      value: 0.1878
      name: Mean Token Overlap (q4+group, 3 prompts × 32 tokens)
    - type: mean_exact_prefix_frac
      value: 0.0729
      name: Mean Exact Prefix Fraction (q4+group, 3 prompts × 32 tokens)
    - type: mean_logprob_delta
      value: -0.172159
      name: Mean Logprob Delta (q4+group, 3 prompts × 32 tokens)
---

# Model Card for Qwen3-0.6B (Aria Quant Bundle, q4)

## Model Details

### Model Description

Qwen3 0.6B is a 600-million-parameter, dense Transformer decoder-only language model developed by the Qwen team at Alibaba Cloud, pre-trained on diverse public corpora and aligned via supervised fine-tuning (SFT) and direct preference optimization (DPO). This distribution is provided by **Aria Compute** as an **aria-quant-bundle** — a uniform 4-bit quantized package using **Hadamard rotation + Lloyd-Max codebook quantization with per-group codebooks** (group size 32). It is optimized for **CPU-only, on-device inference** on mobile phones, edge devices, and single-board computers via the [Aria Engine](https://ariacompute.com) runtime. No GPU or cloud connection is required.

- **Developed by:** Qwen Team (Alibaba Cloud)
- **Quantized and distributed by:** Aria Compute
- **Model type:** Dense Transformer decoder-only (language)
- **Language(s):** English (primary), Chinese, and 20+ additional languages
- **License:** Apache 2.0
- **Finetuned from model:** [Qwen/Qwen3-0.6B](https://huggingface.co/Qwen/Qwen3-0.6B)

### Model Sources

- **Original Repository:** [QwenLM/Qwen3](https://github.com/QwenLM/Qwen3)
- **Original Paper:** Qwen3 Technical Report *(pending)*
- **Aria Compute Dashboard:** [ariacompute.com/dashboard/models](https://ariacompute.com/dashboard/models)
- **Aria Engine:** [ariacompute.com](https://ariacompute.com)

## Uses

### Direct Use

This quantized bundle is intended for **on-device, offline text-generation tasks** on resource-constrained hardware, including:

- On-device chat and conversational assistants
- Real-time text completion and sentence prediction
- Structured tool calling / function calling for mobile and IoT APIs
- Lightweight text embeddings for on-device retrieval and classification
- Short-form summarization of notifications, messages, and local content

### Target Devices

| Platform         | Runtime Memory | Feasibility |
|------------------|----------------|-------------|
| High-end smartphone (8 GB) | ~360 MB | ✅ Recommended |
| Mid-range smartphone (4–6 GB) | ~360 MB | ✅ |
| Budget phone (2–3 GB)     | ~360 MB | ⚠️ Tight, but functional |
| Wearable (1 GB)           | ~360 MB | ⚠️ Tight, but functional |
| Raspberry Pi 5 / SBC (4–8 GB) | ~360 MB | ✅ |
| IoT gateway (1–2 GB)      | ~360 MB | ⚠️ Tight, but functional |

**Memory breakdown (q4, at 4K context):** ~170 MB quantized model weights (mmap) + 112 MB KV cache + 50 MB runtime overhead ≈ 330–360 MB.

### Out-of-Scope Use

- Long-form creative writing (>2K tokens per generation)
- Mathematical theorem proving or complex multi-step reasoning
- Full program synthesis (reliable for short functions only)
- Multimodal input (this model is text-only)
- Real-time audio/speech processing (use Aria speech models)
- Safety-critical decision systems without human oversight

## How to Get Started with the Model

### Download from Aria Compute

Authenticated dashboard users can download the bundle via: https://ariacompute.com/dashboard/models

### Quantization Recipe

This bundle uses the standard **uniform 4-bit** quantization recipe:

| Component | Quantization Strategy | Details |
|-----------|----------------------|---------|
| Attention Q/K/V/O weights | 4-bit | Per-group codebooks (group_size=32), Hadamard pre-processing |
| FFN up/gate/down weights | 4-bit | Per-group codebooks (group_size=32), Hadamard pre-processing |
| RMSNorm weights | FP16 | Preserved at full precision |
| Embedding table | FP16 | Preserved at full precision (tied input/output vocab) |

- **Compression ratio:** ~4–5× smaller than FP16
- **Generation quality:** Mean token overlap 0.1878, exact prefix fraction 0.0729, mean logprob delta −0.172159
- **Calibration-free:** Hadamard rotation + Lloyd-Max codebook, no task-specific calibration data required
- **Baseline recipe:** This is the default 4-bit quantized baseline across the Aria Compute model family

## Model Architecture

Qwen3-0.6B employs a standard **dense Transformer decoder** architecture:

| Parameter | Value |
|-----------|-------|
| Layers | 28 |
| Hidden size | 1,024 |
| FFN intermediate size | 2,816 |
| Attention heads (Query) | 16 |
| Attention heads (KV) | 8 (GQA, group size 2) |
| Head dimension | 128 |
| Activation | SiLU (SwiGLU-style gating) |
| Position encoding | RoPE (θ = 1,000,000) |
| Normalization | RMSNorm (pre-norm) |
| Vocabulary size | ~152,000 |
| Input/output vocab | Tied |

**Design highlights:**
- **GQA (Grouped Query Attention):** 8 KV heads serving 16 query heads — halves KV Cache memory
- **RoPE high base frequency (1M):** Native support for 32K context length
- **Dense FFN + SiLU gating:** High inference efficiency, suitable for on-device use
- **Tied vocab:** Input embedding and output projection weights are shared, saving ~150M parameters

## Bias, Risks, and Limitations

### Limitations

- **Reasoning depth:** Multi-step logical reasoning (≥3 steps) degrades noticeably due to the 0.6B scale. Verify outputs in high-stakes scenarios.
- **Mathematics:** GSM8K and MATH performance is modest. Use larger models for quantitative tasks.
- **Code generation:** Capable of short function completions and one-liners; unreliable for multi-file synthesis or algorithmic problem solving.
- **Factual knowledge:** Limited world knowledge compared to larger models. Always verify factual claims against authoritative sources.
- **Instruction following:** May fail on complex, multi-constraint prompts. Keep instructions short and specific.
- **Quantization drift:** As a uniform 4-bit baseline recipe, generation consistency metrics (token overlap = 0.1878, exact prefix fraction = 0.0729) show moderate divergence from FP16. For higher generation quality, consider the `q326_channel` recipe (recommended generation-quality recipe).

### Bias and Risks

- **Bias:** As with all large language models trained on web-scale data, Qwen3 may reflect societal biases present in its training corpus. Evaluate outputs before deployment in sensitive domains (hiring, healthcare, law).
- **Toxicity:** The base model has been safety-aligned with refusal training. However, no safety filter is exhaustive. Consider an additional output classifier in high-risk environments.
- **Hallucination:** May generate plausible-sounding but factually incorrect information. Implement output verification for critical applications.
- **Dual-use risk:** Text-generation capabilities could be misused for spam, disinformation, or impersonation. Deploy responsibly and in accordance with the Apache 2.0 license terms.

### Recommendations

Users (both direct and downstream) should be made aware of the above risks, biases, limitations, and constraints of the model. We recommend:
- Adding a lightweight output safety classifier for user-facing deployments
- Verifying factual claims with external knowledge bases
- Not using the model for high-stakes decisions without human review