TheDrummer_Snowpiercer-15B-v1-GGUF Open-Source Model - Free Deployment to Boost Text Generation Tasks

Thedrummer Snowpiercer 15B V1 GGUF

Developed by bartowski

A quantized version based on TheDrummer/Snowpiercer-15B-v1 model, using llama.cpp for quantization, suitable for text generation tasks.

Large Language Model Open Source License:MIT #Multi-quantization versions #Low-resource optimization #Text generation

Downloads 4,783

Release Time : 5/14/2025

Model Overview

This is a 15B-parameter large language model with multiple quantization options, adaptable to various hardware environments, supporting efficient text generation.

Model Features

Multiple quantization options

Offers various quantization versions from BF16 to Q2_K, catering to different hardware and performance needs.

High-performance inference

Uses imatrix option for quantization, optimizing inference performance, suitable for running in LM Studio or llama.cpp.

ARM/AVX optimization

Supports online repacking feature, optimizing performance on ARM and AVX hardware.

Model Capabilities

Text generation

Efficient inference

Multi-hardware support

Use Cases

Text generation

Dialogue systems

Used for building intelligent conversational assistants, supporting multi-turn dialogues.

Generates fluent and coherent dialogue responses.

Content creation

Used for generating articles, stories, and other creative content.

Produces high-quality and diverse text content.

🚀 Llamacpp imatrix Quantizations of Snowpiercer-15B-v1 by TheDrummer

This project provides quantized versions of the Snowpiercer-15B-v1 model using llama.cpp. It enables efficient deployment and usage of the model on various hardware platforms.

🚀 Quick Start

Use llama.cpp release b5338 for quantization.
Original model: https://huggingface.co/TheDrummer/Snowpiercer-15B-v1
All quants are made using the imatrix option with the dataset from here.
Run the quantized models in LM Studio.
Run them directly with llama.cpp, or any other llama.cpp based project.

✨ Features

Prompt Format

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

Download Options

You can download a specific file from the following table:

Filename	Quant type	File Size	Split	Description
Snowpiercer-15B-v1-bf16.gguf	bf16	29.96GB	false	Full BF16 weights.
Snowpiercer-15B-v1-Q8_0.gguf	Q8_0	15.92GB	false	Extremely high quality, generally unneeded but max available quant.
Snowpiercer-15B-v1-Q6_K_L.gguf	Q6_K_L	12.62GB	false	Uses Q8_0 for embed and output weights. Very high quality, near perfect, recommended.
Snowpiercer-15B-v1-Q6_K.gguf	Q6_K	12.29GB	false	Very high quality, near perfect, recommended.
Snowpiercer-15B-v1-Q5_K_L.gguf	Q5_K_L	11.07GB	false	Uses Q8_0 for embed and output weights. High quality, recommended.
Snowpiercer-15B-v1-Q5_K_M.gguf	Q5_K_M	10.65GB	false	High quality, recommended.
Snowpiercer-15B-v1-Q5_K_S.gguf	Q5_K_S	10.39GB	false	High quality, recommended.
Snowpiercer-15B-v1-Q4_K_L.gguf	Q4_K_L	9.61GB	false	Uses Q8_0 for embed and output weights. Good quality, recommended.
Snowpiercer-15B-v1-Q4_1.gguf	Q4_1	9.50GB	false	Legacy format, similar performance to Q4_K_S but with improved tokens/watt on Apple silicon.
Snowpiercer-15B-v1-Q4_K_M.gguf	Q4_K_M	9.11GB	false	Good quality, default size for most use cases, recommended.
Snowpiercer-15B-v1-Q4_K_S.gguf	Q4_K_S	8.66GB	false	Slightly lower quality with more space savings, recommended.
Snowpiercer-15B-v1-IQ4_NL.gguf	IQ4_NL	8.64GB	false	Similar to IQ4_XS, but slightly larger. Offers online repacking for ARM CPU inference.
Snowpiercer-15B-v1-Q4_0.gguf	Q4_0	8.63GB	false	Legacy format, offers online repacking for ARM and AVX CPU inference.
Snowpiercer-15B-v1-Q3_K_XL.gguf	Q3_K_XL	8.58GB	false	Uses Q8_0 for embed and output weights. Lower quality but usable, good for low RAM availability.
Snowpiercer-15B-v1-IQ4_XS.gguf	IQ4_XS	8.20GB	false	Decent quality, smaller than Q4_K_S with similar performance, recommended.
Snowpiercer-15B-v1-Q3_K_L.gguf	Q3_K_L	7.99GB	false	Lower quality but usable, good for low RAM availability.
Snowpiercer-15B-v1-Q3_K_M.gguf	Q3_K_M	7.40GB	false	Low quality.
Snowpiercer-15B-v1-IQ3_M.gguf	IQ3_M	6.94GB	false	Medium-low quality, new method with decent performance comparable to Q3_K_M.
Snowpiercer-15B-v1-Q3_K_S.gguf	Q3_K_S	6.71GB	false	Low quality, not recommended.
Snowpiercer-15B-v1-Q2_K_L.gguf	Q2_K_L	6.45GB	false	Uses Q8_0 for embed and output weights. Very low quality but surprisingly usable.
Snowpiercer-15B-v1-IQ3_XS.gguf	IQ3_XS	6.42GB	false	Lower quality, new method with decent performance, slightly better than Q3_K_S.
Snowpiercer-15B-v1-IQ3_XXS.gguf	IQ3_XXS	5.99GB	false	Lower quality, new method with decent performance, comparable to Q3 quants.
Snowpiercer-15B-v1-Q2_K.gguf	Q2_K	5.79GB	false	Very low quality but surprisingly usable.
Snowpiercer-15B-v1-IQ2_M.gguf	IQ2_M	5.35GB	false	Relatively low quality, uses SOTA techniques to be surprisingly usable.
Snowpiercer-15B-v1-IQ2_S.gguf	IQ2_S	4.98GB	false	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.

📦 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/TheDrummer_Snowpiercer-15B-v1-GGUF --include "TheDrummer_Snowpiercer-15B-v1-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/TheDrummer_Snowpiercer-15B-v1-GGUF --include "TheDrummer_Snowpiercer-15B-v1-Q8_0/*" --local-dir ./

You can either specify a new local-dir (TheDrummer_Snowpiercer-15B-v1-Q8_0) or download them all in place (./)

🔧 Technical Details

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

📚 Documentation

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 bot... (The original text seems incomplete here)

📄 License

This project is licensed under the MIT license.

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