Question 1

What is 1bit-MONSTER/Qwen3-30B-A3B-GGUF?

Accepted Answer

--- license: apache-2.0 base_model: - Qwen/Qwen3-30B-A3B tags: - gguf - moe --- # Qwen3-30B-A3B — GGUF (Q4_K_M) Qwen's own Q4_K_M GGUF for Qwen3-30B-A3B (a 30B-total, ~3B-active MoE), re-hosted with measured performance for the [1bit engine](https://github.com/1bit-MONSTER/engine) on Strix Halo. ## Contents - `Qwen3-30B-A3B-Q4_K_M.gguf` ## Measured performance (Strix Halo, Vulkan) pp512: 1230 tok/s · tg128: 76.7 tok/s ## Running it ```bash 1bit serve -m Qwen3-30B-A3B-Q4_K_M.gguf --device vulkan ``` ## Attribution - Model and quantization: [Qwen/Qwen3-30B-A3B-GGUF](https://huggingface.co/Qwen/Qwen3-30B-A3B-GGUF), Apache 2.0. - License: Apache 2.0, inherited from the base model.

Question 2

What license applies to 1bit-MONSTER/Qwen3-30B-A3B-GGUF?

Accepted Answer

License: apache-2.0. Verify terms on Hugging Face before commercial use.

Question 3

How do I run 1bit-MONSTER/Qwen3-30B-A3B-GGUF locally?

Accepted Answer

Download a GGUF file from this page and load it in guIDE or llama.cpp. Pipeline task: text-generation.

Question 4

How much VRAM or disk space does 1bit-MONSTER/Qwen3-30B-A3B-GGUF need?

Accepted Answer

Runs locally from ~17.28 GB disk (24 GB VRAM class GPUs with llama.cpp / guIDE).

1bit-MONSTER/Qwen3-30B-A3B-GGUF overview

Repository Files & Downloads

Model Details

Model README

Qwen3-30B-A3B — GGUF (Q4_K_M)

Contents

Measured performance (Strix Halo, Vulkan)

Running it

Attribution

Run 1bit-MONSTER/Qwen3-30B-A3B-GGUF with guIDE

Model ID	1bit-MONSTER/Qwen3-30B-A3B-GGUF
Author	1bit-MONSTER
Pipeline	—
License	apache-2.0
Base model	Qwen/Qwen3-30B-A3B
Last modified	2026-09-26T13:45:58.000Z