xlangai_Jedi-7B-1080p-GGUF Open Source Model - Balancing Size and Quality with Multiple Quantization Types

Xlangai Jedi 7B 1080p GGUF

Developed by bartowski

This is a Jedi - 7B - 1080p model quantized using llama.cpp, offering multiple quantization types for users to choose from, balancing file size and model quality.

Large Language Model EnglishOpen Source License:Apache-2.0 #Multiple Quantization Levels #Low Memory Optimization #Embedding Output Optimization

Downloads 225

Release Time : 6/1/2025

Model Overview

This model is a quantized version of xlangai's Jedi - 7B - 1080p model, supporting various quantization types suitable for different hardware environments and performance needs.

Model Features

Multiple Quantization Types

Offers various quantization levels from Q2_K to Q8_0, allowing users to select the appropriate level based on hardware conditions and performance requirements.

Embedding/Output Weight Optimization

Certain quantization methods (e.g., Q3_K_XL, Q4_K_L) quantize embedding and output weights as Q8_0 to enhance model quality.

Online Repacking

Supports online repacking of weights to optimize performance for ARM and AVX machines.

Model Capabilities

Text Generation

Multi-turn Dialogue

Operation in Low-Memory Environments

Use Cases

Natural Language Processing

Dialogue Systems

Can be used to build intelligent dialogue systems supporting multi-turn interactions.

Text Generation

Generates high-quality text suitable for content creation, summarization, and similar scenarios.

Low-Resource Environment Applications

Edge Device Deployment

Enables operation on low-memory devices like Raspberry Pi through quantized models.

🚀 Llamacpp imatrix Quantizations of Jedi-7B-1080p by xlangai

This project offers Llama.cpp imatrix quantizations of the Jedi-7B-1080p model. It uses specific Llama.cpp releases for quantization and provides various quantized models with different characteristics for users to choose from.

🚀 Quick Start

You can run these quantized models in LM Studio.
Or run them directly with llama.cpp, or any other llama.cpp based project.

✨ Features

Quantization: Using llama.cpp release b5524 for quantization.
Multiple Quantization Types: Offers a wide range of quantized models with different file sizes, quantization types, and performance characteristics.
Prompt Format: Defines a specific prompt format for interacting with the model.

📦 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/xlangai_Jedi-7B-1080p-GGUF --include "xlangai_Jedi-7B-1080p-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/xlangai_Jedi-7B-1080p-GGUF --include "xlangai_Jedi-7B-1080p-Q8_0/*" --local-dir ./

You can either specify a new local-dir (xlangai_Jedi-7B-1080p-Q8_0) or download them all in place (./)

💻 Usage Examples

Prompt format

<|im_start|>system
{system_prompt}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant

📚 Documentation

Download a file (not the whole branch) from below:

Property	Details
Filename	Jedi-7B-1080p-bf16.gguf, Jedi-7B-1080p-Q8_0.gguf, etc.
Quant type	bf16, Q8_0, Q6_K_L, etc.
File Size	15.24GB, 8.10GB, 6.52GB, etc.
Split	false
Description	Full BF16 weights, Extremely high quality, generally unneeded but max available quant, etc.

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.

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.

Next, you'll need to decide if you want to use an 'I-quant' or a 'K-quant'.

If you don't want to think too much, grab one of the K-quants. These are in format 'QX_K_X', like Q5_K_M.

If you want to get more into the weeds, you can check out this extremely useful feature chart:

llama.cpp feature matrix

But basically, if you're aiming for below Q4, and you're running cuBLAS (Nvidia) or rocBLAS (AMD), you should look towards the I-quants. These are in format IQX_X, like IQ3_M. These are newer and offer better performance for their size.

These I-quants can also be used on CPU, but will be slower than their K-quant equivalent, so speed vs performance is a tradeoff you'll have to decide.

🔧 Technical Details

Quantization is performed using llama.cpp release b5524.
All quants are made using the imatrix option with a dataset from here.

📄 License

This project is licensed under the apache-2.0 license.

Credits

Thank you kalomaze and Dampf for assistance in creating the imatrix calibration dataset. Thank you ZeroWw for the inspiration to experiment with embed/output. Thank you to LM Studio for sponsoring my work.

Want to support my work? Visit my ko-fi page here: https://ko-fi.com/bartowski

Featured Recommended AI Models

Empowering the Future, Your AI Solution Knowledge Base

English 简体中文繁體中文にほんご