%20--%3e%3cdefs%3e%3cstyle%3e%20.st0%20{%20fill:%20%23061b40;%20}%20.st1%20{%20fill:%20%23306af1;%20}%20.st2%20{%20fill:%20%235ce5cf;%20}%20%3c/style%3e%3c/defs%3e%3cg%3e%3cpath%20class='st0'%20d='M55,10.5h9v3h-9v9h12V7.5h-12v3ZM64,19.5h-6v-3h6v3Z'/%3e%3cpolygon%20class='st0'%20points='69%2016.5%2078%2016.5%2078%2019.5%2069%2019.5%2069%2022.5%2081%2022.5%2081%2013.5%2072%2013.5%2072%2010.5%2081%2010.5%2081%207.5%2069%207.5%2069%2016.5'/%3e%3cpolygon%20class='st0'%20points='95%2010.5%2095%207.5%2083%207.5%2083%2022.5%2095%2022.5%2095%2019.5%2086%2019.5%2086%2016.5%2095%2016.5%2095%2013.5%2086%2013.5%2086%2010.5%2095%2010.5'/%3e%3cpath%20class='st0'%20d='M40,1.5v21h11.6l1.4-1.4v-7.6h0c0,0-1.4-1.5-1.4-1.5l1.4-1.4V2.9l-1.4-1.4h-11.6ZM50,19.5h-7v-6h7v6ZM50,10.5h-7v-6h7v6Z'/%3e%3c/g%3e%3cpath%20class='st1'%20d='M23.1,24L14.7,4.8l-4.9,11.2h3.8l-1.8,4H3.3L12.1,0H2C.9,0,0,.9,0,2v20c0,1.1.9,2,2,2h21.1Z'/%3e%3cpath%20class='st2'%20d='M34,0h-16.8l10.6,24h6.2c1.1,0,2-.9,2-2V2C36,.9,35.1,0,34,0ZM32.5,20h-4V4h4v16Z'/%3e%3c/svg%3e)
EN
Qwen Qwen3 30B A3B GGUF
Quantized version based on Qwen/Qwen3-30B-A3B, using llama.cpp for multi-precision quantization, suitable for text generation tasks.
Downloads 79.34k
Release Time : 4/28/2025
Model Overview
This is a quantized version of a 30B-parameter large language model, supporting multiple quantization precision options for efficient inference across different hardware environments.
Model Features
Multiple Quantization Options
Offers 20 different quantization precision model files from Q8_0 to IQ2_XXS to accommodate various hardware requirements.
imatrix Optimization
Uses an improved imatrix dataset for quantization to enhance post-quantization model quality.
Broad Compatibility
Supports LM Studio, llama.cpp, and various projects based on llama.cpp.
Embedding Optimization
In some quantized versions, embeddings and output weights use Q8_0 quantization to maintain precision in critical parts.
Model Capabilities
Text Generation
Dialogue Systems
Content Creation
Use Cases
Dialogue Systems
Intelligent Assistant
Can be used to build intelligent conversational assistants.
Content Generation
Text Creation
Can be used for generating articles, stories, and other textual content.
🚀 Llamacpp imatrix Quantizations of Qwen3-30B-A3B by Qwen
This project provides quantized versions of the Qwen3-30B-A3B model using the llama.cpp library. It allows for efficient deployment and usage of the model on various hardware platforms.
Metadata
| Property | Details |
|---|---|
| Quantized By | bartowski |
| Pipeline Tag | text-generation |
| License | apache-2.0 |
| Base Model | Qwen/Qwen3-30B-A3B |
| Base Model Relation | quantized |
🚀 Quick Start
- Using LM Studio: You can run the quantized models in LM Studio.
- Using llama.cpp: Run the models directly with llama.cpp, or any other llama.cpp based project.
Prompt Format
<|im_start|>system
{system_prompt}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant
✨ Features
- Improved imatrix dataset: The quantizations are made using an improved imatrix option with a dataset from here (augmented with extra synthetic data).
- Multiple quantization types: Offers a wide range of quantization types to suit different hardware and performance requirements.
📦 Installation
Downloading using huggingface-cli
Click to view download instructions
First, make sure you have hugginface-cli installed:
pip install -U "huggingface_hub[cli]"
Then, you can target the specific file you want:
huggingface-cli download bartowski/Qwen_Qwen3-30B-A3B-GGUF --include "Qwen_Qwen3-30B-A3B-Q4_K_M.gguf" --local-dir ./
If the model is bigger than 50GB, it will have been split into multiple files. In order to download them all to a local folder, run:
huggingface-cli download bartowski/Qwen_Qwen3-30B-A3B-GGUF --include "Qwen_Qwen3-30B-A3B-Q8_0/*" --local-dir ./
You can either specify a new local-dir (Qwen_Qwen3-30B-A3B-Q8_0) or download them all in place (./)
💻 Usage Examples
Download a file (not the whole branch) from below:
| Filename | Quant type | File Size | Split | Description |
|---|---|---|---|---|
| Qwen3-30B-A3B-bf16.gguf | bf16 | 61.10GB | true | Full BF16 weights. |
| Qwen3-30B-A3B-Q8_0.gguf | Q8_0 | 32.48GB | false | Extremely high quality, generally unneeded but max available quant. |
| Qwen3-30B-A3B-Q6_K_L.gguf | Q6_K_L | 25.26GB | false | Uses Q8_0 for embed and output weights. Very high quality, near perfect, recommended. |
| Qwen3-30B-A3B-Q6_K.gguf | Q6_K | 25.10GB | false | Very high quality, near perfect, recommended. |
| Qwen3-30B-A3B-Q5_K_L.gguf | Q5_K_L | 21.94GB | false | Uses Q8_0 for embed and output weights. High quality, recommended. |
| Qwen3-30B-A3B-Q5_K_M.gguf | Q5_K_M | 21.74GB | false | High quality, recommended. |
| Qwen3-30B-A3B-Q5_K_S.gguf | Q5_K_S | 21.10GB | false | High quality, recommended. |
| Qwen3-30B-A3B-Q4_1.gguf | Q4_1 | 19.21GB | false | Legacy format, similar performance to Q4_K_S but with improved tokens/watt on Apple silicon. |
| Qwen3-30B-A3B-Q4_K_L.gguf | Q4_K_L | 18.86GB | false | Uses Q8_0 for embed and output weights. Good quality, recommended. |
| Qwen3-30B-A3B-Q4_K_M.gguf | Q4_K_M | 18.63GB | false | Good quality, default size for most use cases, recommended. |
| Qwen3-30B-A3B-Q4_K_S.gguf | Q4_K_S | 17.98GB | false | Slightly lower quality with more space savings, recommended. |
| Qwen3-30B-A3B-Q4_0.gguf | Q4_0 | 17.63GB | false | Legacy format, offers online repacking for ARM and AVX CPU inference. |
| Qwen3-30B-A3B-IQ4_NL.gguf | IQ4_NL | 17.39GB | false | Similar to IQ4_XS, but slightly larger. Offers online repacking for ARM CPU inference. |
| Qwen3-30B-A3B-IQ4_XS.gguf | IQ4_XS | 16.46GB | false | Decent quality, smaller than Q4_K_S with similar performance, recommended. |
| Qwen3-30B-A3B-Q3_K_XL.gguf | Q3_K_XL | 14.86GB | false | Uses Q8_0 for embed and output weights. Lower quality but usable, good for low RAM availability. |
| Qwen3-30B-A3B-Q3_K_L.gguf | Q3_K_L | 14.58GB | false | Lower quality but usable, good for low RAM availability. |
| Qwen3-30B-A3B-Q3_K_M.gguf | Q3_K_M | 14.08GB | false | Low quality. |
| Qwen3-30B-A3B-IQ3_M.gguf | IQ3_M | 14.08GB | false | Medium-low quality, new method with decent performance comparable to Q3_K_M. |
| Qwen3-30B-A3B-Q3_K_S.gguf | Q3_K_S | 13.43GB | false | Low quality, not recommended. |
| Qwen3-30B-A3B-IQ3_XS.gguf | IQ3_XS | 12.74GB | false | Lower quality, new method with decent performance, slightly better than Q3_K_S. |
| Qwen3-30B-A3B-IQ3_XXS.gguf | IQ3_XXS | 12.22GB | false | Lower quality, new method with decent performance, comparable to Q3 quants. |
| Qwen3-30B-A3B-Q2_K_L.gguf | Q2_K_L | 11.21GB | false | Uses Q8_0 for embed and output weights. Very low quality but surprisingly usable. |
| Qwen3-30B-A3B-Q2_K.gguf | Q2_K | 10.91GB | false | Very low quality but surprisingly usable. |
| Qwen3-30B-A3B-IQ2_M.gguf | IQ2_M | 10.43GB | false | Relatively low quality, uses SOTA techniques to be surprisingly usable. |
| Qwen3-30B-A3B-IQ2_S.gguf | IQ2_S | 9.22GB | false | Low quality, uses SOTA techniques to be usable. |
| Qwen3-30B-A3B-IQ2_XS.gguf | IQ2_XS | 9.14GB | false | Low quality, uses SOTA techniques to be usable. |
| Qwen3-30B-A3B-IQ2_XXS.gguf | IQ2_XXS | 8.15GB | false | Very low quality, uses SOTA techniques to be usable. |
Embed/output weights
Some of these quants (Q3_K_XL, Q4_K_L etc) are the standard quantization method with the embeddings and output weights quantized to Q8_0 instead of what they would normally default to.
📚 Documentation
ARM/AVX information
Previously, you would download Q4_0_4_4/4_8/8_8, and these would have their weights interleaved in memory in order to improve performance on ARM and AVX machines by loading up more data in one pass.
Now, however, there is something called "online repacking" for weights. details in this PR. If you use Q4_0 and your hardware would benefit from repacking weights, it will do it automatically on the fly.
As of llama.cpp build b4282 you will not be able to run the Q4_0_X_X files and will instead need to use Q4_0.
Additionally, if you want to get slightly better quality for , you can use IQ4_NL thanks to this PR which will also repack the weights for ARM, though only the 4_4 for now. The loading time may be slower but it will result in an overall speed incrase.
Click to view Q4_0_X_X information (deprecated)
I'm keeping this section to show the potential theoretical uplift in performance from using the Q4_0 with online repacking.
Click to view benchmarks on an AVX2 system (EPYC7702)
| model | size | params | backend | threads | test | t/s | % (vs Q4_0) |
|---|---|---|---|---|---|---|---|
| qwen2 3B Q4_0 | 1.70 GiB | 3.09 B | CPU | 64 | pp512 | 204.03 ± 1.03 | 100% |
| qwen2 3B Q4_0 | 1.70 GiB | 3.09 B | CPU | 64 | pp1024 | 282.92 ± 0.19 | 100% |
| qwen2 3B Q4_0 | 1.70 GiB | 3.09 B | CPU | 64 | pp2048 | 259.49 ± 0.44 | 100% |
| qwen2 3B Q4_0 | 1.70 GiB | 3.09 B | CPU | 64 | tg128 | 39.12 ± 0.27 | 100% |
| qwen2 3B Q4_0 | 1.70 GiB | 3.09 B | CPU | 64 | tg256 | 39.31 ± 0.69 | 100% |
| qwen2 3B Q4_0 | 1.70 GiB | 3.09 B | CPU | 64 | tg512 | 40.52 ± 0.03 | 100% |
| qwen2 3B Q4_K_M | 1.79 GiB | 3.09 B | CPU | 64 | pp512 | 301.02 ± 1.74 | 147% |
| qwen2 3B Q4_K_M | 1.79 GiB | 3.09 B | CPU | 64 | pp1024 | 287.23 ± 0.20 | 101% |
| qwen2 3B Q4_K_M | 1.79 GiB | 3.09 B | CPU | 64 | pp2048 | 262.77 ± 1.81 | 101% |
| qwen2 3B Q4_K_M | 1.79 GiB | 3.09 B | CPU | 64 | tg128 | 18.80 ± 0.99 | 48% |
| qwen2 3B Q4_K_M | 1.79 GiB | 3.09 B | CPU | 64 | tg256 | 24.46 ± 3.04 | 83% |
| qwen2 3B Q4_K_M | 1.79 GiB | 3.09 B | CPU | 64 | tg512 | 36.32 ± 3.59 | 90% |
| qwen2 3B Q4_0_8_8 | 1.69 GiB | 3.09 B | CPU | 64 | pp512 | 271.71 ± 3.53 | 133% |
| qwen2 3B Q4_0_8_8 | 1.69 GiB | 3.09 B | CPU | 64 | pp1024 | 279.86 ± 45.63 | 100% |
| qwen2 3B Q4_0_8_8 | 1.69 GiB | 3.09 B | CPU | 64 | pp2048 | 320.77 ± 5.00 | 124% |
| qwen2 3B Q4_0_8_8 | 1.69 GiB | 3.09 B | CPU | 64 | tg128 | 43.51 ± 0.05 | 111% |
| qwen2 3B Q4_0_8_8 | 1.69 GiB | 3.09 B | CPU | 64 | tg256 | 43.35 ± 0.09 | 110% |
| qwen2 3B Q4_0_8_8 | 1.69 GiB | 3.09 B | CPU | 64 | tg512 | 42.60 ± 0.31 | 105% |
Q4_0_8_8 offers a nice bump to prompt processing and a small bump to text generation
Which file should I choose?
Click here for details
A great write up with charts showing various performances is provided by Artefact2 here
The first thing to figure out is how big a model you can run. To do this, you'll need to figure out how much RAM and/or VRAM you have.
If you want your model running as FAST as possible, you'll want to fit the whole thing on your GPU's VRAM. Aim for a quant with a file size 1 - 2GB smaller than your GPU's total VRAM.
If you want the absolute maximum quality, add both your system RAM and your GPU's VRAM together, then similarly grab a quant with a file size 1 - 2GB smaller than that total.
📄 License
This project is licensed under the apache-2.0 license.
Phi 2 GGUF
Other
Phi-2 is a small yet powerful language model developed by Microsoft, featuring 2.7 billion parameters, focusing on efficient inference and high-quality text generation.
Large Language Model Supports Multiple Languages
P
TheBloke
41.5M
205
Roberta Large
MIT
A large English language model pre-trained with masked language modeling objectives, using improved BERT training methods
Large Language Model English
R
FacebookAI
19.4M
212
Distilbert Base Uncased
Apache-2.0
DistilBERT is a distilled version of the BERT base model, maintaining similar performance while being more lightweight and efficient, suitable for natural language processing tasks such as sequence classification and token classification.
Large Language Model English
D
distilbert
11.1M
669
Llama 3.1 8B Instruct GGUF
Meta Llama 3.1 8B Instruct is a multilingual large language model optimized for multilingual dialogue use cases, excelling in common industry benchmarks.
Large Language Model English
L
modularai
9.7M
4
Xlm Roberta Base
MIT
XLM-RoBERTa is a multilingual model pretrained on 2.5TB of filtered CommonCrawl data across 100 languages, using masked language modeling as the training objective.
Large Language Model Supports Multiple Languages
X
FacebookAI
9.6M
664
Roberta Base
MIT
An English pre-trained model based on Transformer architecture, trained on massive text through masked language modeling objectives, supporting text feature extraction and downstream task fine-tuning
Large Language Model English
R
FacebookAI
9.3M
488
Opt 125m
Other
OPT is an open pre-trained Transformer language model suite released by Meta AI, with parameter sizes ranging from 125 million to 175 billion, designed to match the performance of the GPT-3 series while promoting open research in large-scale language models.
Large Language Model English
O
facebook
6.3M
198
1
A pretrained model based on the transformers library, suitable for various NLP tasks
Large Language Model
Transformers
Transformers1
unslothai
6.2M
1
Llama 3.1 8B Instruct
Llama 3.1 is Meta's multilingual large language model series, featuring 8B, 70B, and 405B parameter scales, supporting 8 languages and code generation, with optimized multilingual dialogue scenarios.
Large Language Model Transformers Supports Multiple Languages
Transformers Supports Multiple LanguagesL
meta-llama
5.7M
3,898
T5 Base
Apache-2.0
The T5 Base Version is a text-to-text Transformer model developed by Google with 220 million parameters, supporting multilingual NLP tasks.
Large Language Model Supports Multiple Languages
T
google-t5
5.4M
702
Featured Recommended AI Models