> ## Documentation Index
> Fetch the complete documentation index at: https://mintlify.com/ikawrakow/ik_llama.cpp/llms.txt
> Use this file to discover all available pages before exploring further.

# Supported models

> Model families supported by ik_llama.cpp

The following model families are supported. Download `.gguf` files from HuggingFace and pass them to `--model`.

| Model            | Notes                                     |
| ---------------- | ----------------------------------------- |
| LLaMA-4          | Vision and text variants                  |
| LLaMA-3-Nemotron | NVIDIA reasoning model                    |
| Qwen3            | Dense and instruct variants               |
| Qwen3-VL         | Vision-language variant                   |
| Qwen3-Next       | Recurrent hybrid; use `--ctx-checkpoints` |
| Qwen3.5-MoE      | MoE variant; use `--ctx-checkpoints`      |
| GLM-4 / 4.5 / 5  | Includes AIR, Flash, and MoE sub-variants |
| Command-A        | Cohere Command-A                          |
| BitNet b1.58     | 1-bit quantization natively supported     |
| DeepSeek-V3 / R1 | MLA-based MoE models                      |
| Gemma 3          | Google Gemma 3 family                     |
| Kimi-2           | Moonshot Kimi-2                           |
| grok-2           | xAI grok-2                                |
| SmolLM3          | HuggingFace compact model                 |
| ministral3       | Mistral 3B                                |
| Hunyuan          | Tencent Hunyuan                           |

<Note>
  DeepSeek-V3 and DeepSeek-R1 use Multi-head Latent Attention (MLA). Pass `-mla 3`
  (the default) for best performance. Lower values reduce memory use at a speed cost.
</Note>

<Warning>
  Do not use Unsloth models with `_XL` in their name that contain `f16` tensors.
  These models are incompatible with ik\_llama.cpp. Unsloth `_XL` models that do
  not use `f16` tensors are fine.
</Warning>