Qwen3 30B A1.5B High Speed

🚀 Qwen3-30B-A1.5B-High-Speed - AKA: "Punch IT!"

This repository offers a high - speed version of the Qwen model. It can generate various formats like GGUF, GPTQ, EXL2, AWQ, HQQ, etc., and the source code can be used directly. By adjusting the number of active experts, it nearly doubles the model's speed and uses fewer parameters, making it suitable for simpler use cases.

✨ Features

• High - speed operation: By reducing the number of active experts from 8 to 4 out of 128, the model's speed is nearly doubled, and it uses 1.5B (out of 30B) parameters instead of 3B.
• Multiple formats: The full - precision source code can generate GGUF, GPTQ, EXL2, AWQ, HQQ and other formats.
• Large context size: It supports a context size of 32K + 8K for output (40k total).
• Template support: It can use Jinja Template or CHATML template.

📦 Installation

No installation steps are provided in the original document, so this section is skipped.

💻 Usage Examples

Basic Usage

The following shows an example of generating text with this model (Q4KS, CPU). The generation is based on a science - fiction prompt.

PROMPT:
Science Fiction: The Last Transmission - Write a story that takes place entirely within a spaceship's cockpit as the sole surviving crew member attempts to send a final message back to Earth before the ship's power runs out. The story should explore themes of isolation, sacrifice, and the importance of human connection in the face of adversity. If the situation calls for it, have the character(s) curse and swear to further the reader's emotional connection to them. 800 - 1000 words.

Advanced Usage

During the generation process, the model first analyzes the prompt in detail, including aspects such as scene setting, theme exploration, conflict design, and character development. Here is the model's thinking process:

Thought for 47.29 seconds

Okay, I need to write a science fiction story based on the given prompt. The user wants the story to take place entirely in a spaceship's cockpit, focusing on the last surviving crew member trying to send a final message before the ship's power runs out. Themes are isolation, sacrifice, and human connection. Also, include some cursing to add emotional weight.

First, I should start by setting the scene. The cockpit needs to feel cramped and desperate. Maybe describe the flickering lights and the hissing sounds of the ship's systems failing. The main character is alone, so I need to show their loneliness. Maybe they have a log or something to talk to themselves, but since it's the cockpit, perhaps they're just trying to get through the message.

Next, the themes. Isolation is straightforward—they're the only one left. But how to show sacrifice? Maybe they stayed behind to make sure the message gets through, knowing they won't make it. Human connection could come through flashbacks or memories, but since the story is in the cockpit, maybe they're remembering a loved one, like a child or partner, to keep them going.

I need to include some swearing. Maybe the protagonist curses when they realize something's not working, or when they're under stress. But it shouldn't be too over the top. Maybe they curse at the ship for failing them, or at themselves for not being able to fix it.

The structure: Start with the character working on the controls, trying to send the message. Then show their internal struggle. Maybe flashbacks? Wait, the user said the story should take place entirely within the cockpit. So maybe no flashbacks. Just the present moment, with internal monologue.

Conflict: The ship is failing, power is running out. They need to send the message before they lose power. Maybe there's a countdown or a limited time. Also, maybe the ship is damaged in a way that it's irreversible.

Character development: The protagonist is determined, maybe a bit stubborn. They care about relaying the message, which could be a warning about something, like a virus or an alien threat. But since the prompt doesn't specify, maybe it's more about the human aspect—like they're the last, and they want to make sure someone knows what happened.

Dialogue: Since it's the cockpit, maybe they talk to themselves, or to the ship. Or maybe there's a voice in the comms? Wait, but the prompt says the story is entirely within the cockpit. So no one else is there except the main character. So it's all internal, except for maybe a log entry.

Wait, the user said "the sole surviving crew member attempts to send a final message back to Earth." So the message is for Earth. So maybe the protagonist is trying to record a message, but the ship is failing. Or maybe they're trying to send a distress signal, but the systems are failing.

Let me outline:

- Open with the cockpit's deteriorating condition. Maybe the life support is failing, or the power is out. The protagonist is trying to keep the comms on.
- They're alone, so they talk to the ship, maybe. "Come on, you piece of crap, hold together."
- Flashbacks aren't allowed, per the user's instruction (since it's all in the cockpit), so internal thoughts are key.
- The message they need to send is important. Maybe a warning about something, but also their own fear.
- The story should end with them managing to send the message, but knowing they won't survive, or maybe the message gets through just in time.

Including swearing: Maybe when they're frustrated with the systems not working, or when they realize the power is dying. "F***ing hell," "God damn it," etc.

Need to make sure the themes are present. Isolation: being the only one left. Sacrifice: giving their life to send the message. Human connection: maybe they think of someone before they die, or the act of sending the message is about connecting with others back home.

Possible structure:

1. Start in the cockpit, power failing, protagonist working frantically.
2. Flashbacks? Wait, no—since it's all in the cockpit, maybe not. But internal monologue can reflect on their past.
3. The protagonist's internal struggle: fear of death, but also duty to send the message.
4. Technical difficulties with the ship, leading to a climax where they get the message out, then succumb.

Now, writing the story with these elements. Keep it tight, 800 - 1000 words. Make the protagonist relatable, their fear and determination clear. Use short, punchy sentences to build tension. Include specific details about the ship's systems, maybe some technical jargon to make it realistic. Maybe the protagonist is an engineer or someone who knows the ship well, which helps in the struggle to keep it running.

Possible name for the character? Maybe not necessary, but a few names could be used. Or just "they" and "the pilot."

Also, the title: "The Last Transmission" is given, so the story should reflect that—sending a message, even if no one's there to receive it, or in this case, maybe they do.

Need to avoid clichés, but it's a common sci - fi trope. Make it fresh with emotional depth.

Potential pitfalls: Making the protagonist too passive, not showing their struggle enough. Need to show, not tell. Also, ensuring the themes are woven naturally into the narrative.

Okay, time to start drafting.

And here is the generated output:

The cockpit reeked of burnt circuitry and sweat, a stench that clung to my skin like a second, cursed flesh. My fingers danced over the controls, but the readouts spat back static—useless, just like the rest of this rustbucket. "Crawl, you piece of junk," I growled, slapping the console until my knuckles cracked. "Crawl!"

The ship groaned in response, a sound that might have been a moan if I were the superstitious type. I wasn't. Not really. Not anymore. Just a tired engineer with a death wish and a terminal case of bad luck. The Vanguard had been my pride before it became my prison. Now? Now it was a coffin, and I was the corpse inside, begging for the black to take me.

"Comm - link online," I rasped, watching the screen flicker. Nothing. Just the same hollow gray that had greeted me every time I tried to send this goddamn message. A laugh clawed up my throat—bitter, raw. Great. The AI's gone and left me high an

📚 Documentation

Model Information

Context Size

The context size is 32K + 8K for output (40k total).

Templates

It can use Jinja Template or CHATML template.

Other Versions

• 12 experts version: [ https://huggingface.co/DavidAU/Qwen3 - 30B - A4.5B - 12 - Cooks ]
• 16 experts version: [ https://huggingface.co/DavidAU/Qwen3 - 30B - A6B - 16 - Extreme ]
• 16 experts, 128k context version: [ https://huggingface.co/DavidAU/Qwen3 - 30B - A6B - 16 - Extreme - 128k - context ]
• 24 experts version: [ https://huggingface.co/DavidAU/Qwen3 - 30B - A7.5B - 24 - Grand - Brainstorm ]

NEO Imatrix Quants / Imatrix Max Quants

Available at 64K context: [ https://huggingface.co/DavidAU/Qwen3 - 30B - A1.5B - High - Speed - NEO - Imatrix - MAX - gguf ]

System Role

You may or may not need to set the system role as most times Qwen3s generate their own reasoning/thinking blocks. The system role is as follows:

You are a deep thinking AI, you may use extremely long chains of thought to deeply consider the problem and deliberate with yourself via systematic reasoning processes to help come to a correct solution prior to answering. You should enclose your thoughts and internal monologue inside <think> </think> tags, and then provide your solution or response to the problem.

For how to "set" the system role in various LLM/AI apps, see the document "Maximizing - Model - Performance - All..."

Settings and Optimization

If you are going to use this model (source, GGUF or a different quant), please review this document for critical parameter, sampler and advance sampler settings (for multiple AI/LLM aps):

[ https://huggingface.co/DavidAU/Maximizing - Model - Performance - All - Quants - Types - And - Full - Precision - by - Samplers_Parameters ]

This document details methods to enhance operations for all models, regardless of "model class". It also provides settings that can be used for any model, from any repo, all quants, and source code operation.

Additional Note

It is strongly recommended to visit the DavidAU GGUF repo for more details on using this model, especially if it is a "Class 3" or "Class 4" model, to get maximum performance. For full information about this model, including details, context limits, special usage notes, models used for creation, templates, example generations, and GGUF quants, please go to:

[ https://huggingface.co/DavidAU/Qwen3 - 30B - A1.5B - High - Speed - NEO - Imatrix - MAX - gguf ]

🔧 Technical Details

No specific technical implementation details are provided in the original document, so this section is skipped.

📄 License

No license information is provided in the original document, so this section is skipped.