Unsloth

ERNIE-Image-Turbo-GGUF

Baidu

This is a GGUF quantized version of [ERNIE-Image-Turbo](https://huggingface.co/baidu/ERNIE-Image-Turbo). unsloth/ERNIE-Image-Turbo-GGUF uses [Unsloth Dynamic...

GLM-5.3-Flash-GGUF

Zhipu

👋 Join our WeChat or Discord community. 📖 Check out the GLM-5.3-Flash blog and GLM-5 Technical report. 📍 Use GLM-5.3-Flash API services on Z.ai API Platform....

Inkling-Small-GGUF

Inkling-Small is a general-purpose multimodal model that accepts text, image and audio inputs and generates text outputs. It is intended for use in English a...

Muse-Glimmer-30B-GGUF

**Authors:** Meta Superintelligence Lab **Model Release Date:** August 2026 **License:** [Apache 2.0](https://www.apache.org/licenses/LICENSE-2.0) Muse Glimm...

Qwen3.8-Flash-Next-GGUF

Qwen

As the frontier of foundation models pushes toward ever-larger parameter counts and ever-longer context windows, the question is no longer just how much we c...

Z-Image-GGUF

This is a GGUF quantized version of [Z-Image](https://huggingface.co/Tongyi-MAI/Z-Image). unsloth/Z-Image-GGUF uses [Unsloth Dynamic 2.0](https://docs.unslot...

gemma-4-31B-it-qat-GGUF

Google

This model ships a Multi-Token Prediction drafter at the repo root (`mtp-gemma-4-31B-it.gguf`, a near-lossless smart Q4_0). A recent llama.cpp auto-discovers...

inkling-GGUF

Inkling is a general-purpose multimodal model that accepts text, image and audio inputs and generates text outputs. It is intended for use in English and oth...

unsloth/GLM-4.7-Flash

Zhipu · 31.2B

> [!NOTE] > Includes Unsloth **chat template fixes**! For `llama.cpp`, use `--jinja` > 👋 Join our Discord community. 📖 Check out the GLM-4.7 technical blog, ...

unsloth/GLM-4.7-Flash-FP8-Dynamic

Zhipu · 30B

FP8 Dynamically quantized by Unsloth for fast and premium inference.You can read our [vLLM deployment guide](https://unsloth.ai/docs/models/glm-4.7-flash#glm...

unsloth/GLM-4.7-Flash-GGUF

Zhipu

- **Repeat penalty: Disable it, or set `--repeat-penalty 1.0`** You can now use Z.ai's recommended parameters and get great results: - For general use-case: ...

unsloth/Llama-3.1-8B-Instruct

Meta · 8B

The Meta Llama 3.1 collection of multilingual large language models (LLMs) is a collection of pretrained and instruction tuned generative models in 8B, 70B a...

unsloth/Llama-3.2-1B-Instruct

Meta · 1.2B

We have a free Google Colab Tesla T4 notebook for Llama 3.2 (3B) here: https://colab.research.google.com/drive/1T5-zKWM_5OD21QHwXHiV9ixTRR7k3iB9?usp=sharing ...

unsloth/Llama-3.2-1B-Instruct-GGUF

Meta · 1B

16bit, 8bit, 6bit, 5bit, 4bit, 3bit and 2bit uploads avaliable. We have a free Google Colab Tesla T4 notebook for Llama 3.2 (3B) here: https://colab.research...

unsloth/Llama-3.2-1B-Instruct-unsloth-bnb-4bit

Meta · 1.3B

*Dynamic 4-bit: Unsloth's [Dynamic 4-bit Quants](https://unsloth.ai/blog/dynamic-4bit) selectively avoids quantizing certain parameters, greatly increase acc...

unsloth/Llama-3.2-3B-Instruct

Meta · 3.2B

We have a free Google Colab Tesla T4 notebook for Llama 3.2 (3B) here: https://colab.research.google.com/drive/1T5-zKWM_5OD21QHwXHiV9ixTRR7k3iB9?usp=sharing ...

unsloth/Llama-3.2-3B-Instruct-unsloth-bnb-4bit

Meta · 3.3B

We have a free Google Colab Tesla T4 notebook for Llama 3.2 (3B) here: https://colab.research.google.com/github/unslothai/notebooks/blob/main/nb/Llama3.1_(8B...

unsloth/Meta-Llama-3.1-8B-Instruct

Meta · 8B

We have a free Google Colab Tesla T4 notebook for Llama 3.1 (8B) here: https://colab.research.google.com/drive/1Ys44kVvmeZtnICzWz0xgpRnrIOjZAuxp?usp=sharing ...

unsloth/Meta-Llama-3.1-8B-Instruct-bnb-4bit

Meta · 8.2B

We have a free Google Colab Tesla T4 notebook for Llama 3.1 (8B) here: https://colab.research.google.com/drive/1Ys44kVvmeZtnICzWz0xgpRnrIOjZAuxp?usp=sharing ...

unsloth/Nemotron-3-Nano-30B-A3B-GGUF

NVIDIA · 30B

- Note `` and `` are separate tokens, so use `--special` if needed. - You can also fine-tune the model with Unsloth. **Model Developer:** NVIDIA Corporation ...

unsloth/Qwen2-7B

Qwen · 7.6B

We have a Google Colab Tesla T4 notebook for Qwen2 7b here: https://colab.research.google.com/drive/1mvwsIQWDs2EdZxZQF9pRGnnOvE86MVvR?usp=sharing And a Colab...

unsloth/Qwen2.5-3B-Instruct-unsloth-bnb-4bit

Qwen · 3.2B

We have a free Google Colab Tesla T4 notebook for Qwen2.5 (7B) here: https://colab.research.google.com/github/unslothai/notebooks/blob/main/nb/Qwen2.5_(7B)-A...

unsloth/Qwen2.5-7B

Qwen · 7.6B

We have a Qwen 2.5 (all model sizes) [free Google Colab Tesla T4 notebook](https://colab.research.google.com/drive/1Kose-ucXO1IBaZq5BvbwWieuubP7hxvQ?usp=shar...

unsloth/Qwen2.5-7B-Instruct

Qwen · 7.6B

We have a Qwen 2.5 (all model sizes) [free Google Colab Tesla T4 notebook](https://colab.research.google.com/drive/1Kose-ucXO1IBaZq5BvbwWieuubP7hxvQ?usp=shar...

unsloth/Qwen2.5-7B-Instruct-bnb-4bit

Qwen · 7.8B

We have a Qwen 2.5 (all model sizes) [free Google Colab Tesla T4 notebook](https://colab.research.google.com/drive/1Kose-ucXO1IBaZq5BvbwWieuubP7hxvQ?usp=shar...

unsloth/Qwen3-0.6B-unsloth-bnb-4bit

Qwen · 609M

- Fine-tune Qwen3 (14B) for free using our Google [Colab notebook here](https://docs.unsloth.ai/get-started/unsloth-notebooks)! - Read our Blog about Qwen3 s...

unsloth/Qwen3-1.7B-unsloth-bnb-4bit

Qwen · 1.8B

- Fine-tune Qwen3 (14B) for free using our Google [Colab notebook here](https://docs.unsloth.ai/get-started/unsloth-notebooks)! - Read our Blog about Qwen3 s...

unsloth/Qwen3-14B-unsloth-bnb-4bit

Qwen · 15.2B

- Fine-tune Qwen3 (14B) for free using our Google [Colab notebook here](https://docs.unsloth.ai/get-started/unsloth-notebooks)! - Read our Blog about Qwen3 s...

unsloth/Qwen3-4B-Base

Qwen · 4B

Qwen3 is the latest generation of large language models in Qwen series, offering a comprehensive suite of dense and mixture-of-experts (MoE) models. Building...

unsloth/Qwen3-4B-Instruct-2507-unsloth-bnb-4bit

Qwen · 4.1B

We introduce the updated version of the **Qwen3-4B non-thinking mode**, named **Qwen3-4B-Instruct-2507**, featuring the following key enhancements: - **Signi...

unsloth/Qwen3-Coder-30B-A3B-Instruct-GGUF

Qwen · 30B

- Fine-tune Qwen3 (14B) for free using our Google [Colab notebook](https://docs.unsloth.ai/get-started/unsloth-notebooks)! - Read our Blog about Qwen3 suppor...

unsloth/Qwen3-Coder-Next-GGUF

Qwen

- **Feb 19 update**: Tool-calling should now be even better after llama.cpp fixes parsing. - **Quantization benchmarks**: See third-party Aider, LiveCodeBenc...

unsloth/gpt-oss-120b-BF16

OpenAI · 116.8B

- Read our Blog about gpt-oss support: [unsloth.ai/blog/gpt-oss](https://unsloth.ai/blog/gpt-oss) - View the rest of our notebooks in our [docs here](https:/...

unsloth/gpt-oss-120b-GGUF

OpenAI · 120B

> [!NOTE] > The F16 quant is gpt-oss in its **original** precision. All GGUFs have our fixes. [Read our guide here.](https://docs.unsloth.ai/basics/gpt-oss) ...

unsloth/gpt-oss-20b

OpenAI · 21.5B

Welcome to the gpt-oss series, [OpenAI’s open-weight models](https://openai.com/open-models) designed for powerful reasoning, agentic tasks, and versatile de...

unsloth/gpt-oss-20b-BF16

OpenAI · 20.9B

Welcome to the gpt-oss series, [OpenAI’s open-weight models](https://openai.com/open-models) designed for powerful reasoning, agentic tasks, and versatile de...

unsloth/gpt-oss-20b-GGUF

OpenAI · 20B

- Fine-tune gpt-oss-20b for free using our [Google Colab notebook](https://colab.research.google.com/github/unslothai/notebooks/blob/main/nb/gpt-oss-(20B)-Fi...

unsloth/gpt-oss-20b-unsloth-bnb-4bit

OpenAI · 20.9B

- Read our Blog about gpt-oss support: [unsloth.ai/blog/gpt-oss](https://unsloth.ai/blog/gpt-oss) - View the rest of our notebooks in our [docs here](https:/...

unsloth/mistral-7b-v0.3-bnb-4bit

Mistral · 7.5B

We have a Google Colab Tesla T4 notebook for Mistral v3 7b here: https://colab.research.google.com/drive/1_yNCks4BTD5zOnjozppphh5GzMFaMKq_?usp=sharing For co...