GraySoft
Projects Models Compare Cloud benchmarks FAQ Download guIDE →
Model Intelligence Sheet

jamiefutch/gemma-4-26B-A4B-it-MXFP4_MOE-GGUF overview

These are MXFP4 quantizations of the model gemma 4 26B A4B it https://huggingface.co/google/gemma 4 26B A4B it Quick Start 1. Download the latest release of ll…

ggufimage-text-to-textbase_model:google/gemma-4-26B-A4B-itbase_model:quantized:google/gemma-4-26B-A4B-itendpoints_compatibleregion:usconversational

Runs locally from ~1.11 GB disk (4 GB VRAM class GPUs with llama.cpp / guIDE).

Downloads
0
Likes
1
Pipeline
image-text-to-text

Repository Files & Downloads

5 GGUF files detected
Direct downloads for local inference
FileTypeQuantizationSizeLink
gemma-4-26B-A4B-it-MXFP4_MOE.ggufGGUFGGUF14.36 GBDownload
gemma-4-26B-A4B-it-MXFP4_MOE_BF16.ggufGGUFBF1615.80 GBDownload
gemma-4-26B-A4B-it-MXFP4_MOE_F16.ggufGGUFF1615.80 GBDownload
gemma-4-26B-A4B-it-mmproj-BF16.ggufGGUFBF161.11 GBDownload
gemma-4-26B-A4B-it-mmproj-F32.ggufGGUFF322.13 GBDownload

Model Details

Model IDjamiefutch/gemma-4-26B-A4B-it-MXFP4_MOE-GGUF
Authorjamiefutch
Pipelineimage-text-to-text
License
Base modelgoogle/gemma-4-26B-A4B-it
Last modified2026-07-06T10:48:16.000Z

Model README

---

pipeline_tag: image-text-to-text

base_model:

  • google/gemma-4-26B-A4B-it

---

These are MXFP4 quantizations of the model gemma-4-26B-A4B-it

Quick Start

  1. Download the latest release of llama.cpp.
  2. Download your preferred model variant from below.
  3. For the mmproj file, it is recommended to use the F32 version for the best visual processing results. F32 > BF16 > F16

Which version should I choose?

All variants use MXFP4 for the MoE (Mixture of Experts) weights to keep the model efficient. The difference lies in how the remaining tensors are handled:

| Variant | Quality | Performance | Size | Recommendation |

| :--- | :--- | :--- | ---: | :--- |

| BF16 | ⭐⭐⭐ | Variable* | 15.80GiB | Best for maximum accuracy; original unquantized weights. |

| F16 | ⭐⭐ | Fast | 15.80GiB | Great alternative if BF16 is slow on your hardware. |

| Q8 | ⭐ | Fastest | 14.36GiB | Balanced performance and memory usage. |

Note: On some older architectures, BF16 may be slower than F16.

Check that your GPU supports native BF16

Read the guide from unsloth in order to set up the model's recommended settings:

The official chat template has been updated from Google. If you do not want to download the model again, you can just tell llama.cpp to use the new chat template.

Run jamiefutch/gemma-4-26B-A4B-it-MXFP4_MOE-GGUF with guIDE

Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.

Download guIDE → · Browse 524k+ models · Compare models

Source: Hugging Face · Compare models