RedHatAI/gemma-4-26B-A4B-it-NVFP4

image-text-to-text model by RedHatAI

Open original source ↗

From the publisher

Model card & documentation

Source preview

Read the publisher’s intended use, setup instructions, evaluations and limitations. The original model card is the source of truth.

gemma-4-26B-A4B-it-NVFP4 This model is a quantized version of google/gemma-4-26B-A4B-it. It was evaluated on several tasks to assess its quality in comparison to the unquantized model. This model was obtained by quantizing the weights and activations of google/gemma-4-26B-A4B-it to NVFP4 data type, ready for inference with vLLM. This optimization reduces the number of bits per parameter from 16 to 4, reducing the disk size and GPU memory requirements by approximately 75%. Weights are quantized to FP4 with a group size of 16, and activations are quantized to FP4 with local per-group scaling. Only the weights and activations of the linear operators within transformer blocks are quantized using LLM Compressor. Vision tower, embedding, output head, and MoE router layers are kept in their original precision. This model can be deployed using vLLM. For detailed instructions including multimodal inference, thinking mode, function calling, and benchmarking, see the Gemma 4 26B-A4B vLLM usage guide.…

RedHatAI/gemma-4-26B-A4B-it-NVFP4 on Hugging Face A short preview, not the full document.

Read the full model card ↗ · Preview checked 2026-11-16T07:05:15.027Z

Inside the original model card — Document outline
  1. Model Overview
  2. Model Optimizations
  3. Deployment
  4. Use with vLLM
  5. Creation
  6. Evaluation
  7. Accuracy
  8. Without thinking
  9. With thinking
  10. Reproduction
  11. GSM8K Platinum (lm-eval, 0-shot, 3 repetitions)
  12. MMLU-Pro (lm-eval, 0-shot, 3 repetitions)

Headings are captured from the source. Links open the publisher’s document, not a locally hosted copy.

Links from the model card

References supplied by the publisher, not independently verified endorsements. Check the destination before downloading files or entering credentials.

Documentation belongs to its respective authors. Reported project/model license: apache-2.0. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.

Model overview

RedHatAI/gemma-4-26B-A4B-it-NVFP4 is a image-text-to-text model repository published by RedHatAI on Hugging Face. The source reports the transformers library.

This page summarizes Hub metadata. For intended use, training data, evaluation results and limitations, consult the original model card.

Model facts

Task
image-text-to-text
Library
transformers
Recent downloads (30 days)
742,659
Cumulative likes
46
Hugging Face trending score
0
Reported safetensors parameters
25,805,936,206
Architecture
Gemma4ForConditionalGeneration
License
apache-2.0
Access
Not gated by Hugging Face
Created
2026-04-05T20:47:47.000Z
Last modified
2026-08-13T13:09:09.000Z

Compatibility and lineage

Language coverage was not reported.

Reported base models: google/gemma-4-26B-A4B-it

Parameter count is not a RAM/VRAM requirement. Check precision, quantization, context length and runtime compatibility in the model card; no hardware or API-cost claim is inferred here.

Use and evaluate

Check license terms and access requirements first. Review the model card’s documented loading instructions, evaluations and safety limitations. Benchmark scores are not imported by this directory, and popularity is not an accuracy ranking.

No model weights are downloaded or executed by AltAPIs. Never enable remote model code without reviewing it.

Model card and usage instructions

Model files and configuration

Community discussion

Source and freshness

Source: Hugging Face Hub. Metadata observed 2026-11-16T07:01:13.498Z. Daily imports are snapshots, not real-time monitoring.

Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.

Open original source

Related models

microsoft/Florence-2-base

ISTA-DASLab/Qwen3.8-Flash-Next-GSQ-RCO-GGUF

Qwen/Qwen3-VL-8B-Instruct

Qwen/Qwen3.8-27B

google/gemma-4-31B-it

zai-org/GLM-5.3-Flash