nvidia / text-generation updated 2 months ago

Gemma-4-26B-A4B-NVFP4

Name: Gemma-4-26B-A4B-NVFP4
Author: nvidia

Gemma 4 26B IT is an open multimodal model built by Google DeepMind that handles text and image inputs, can process video as sequences of frames, and generates text output. It is designed to deliver frontier-level performance for reasoning, agentic workflows, coding, and multimodal understanding on consumer GPUs and workstations, with a 256K-token context window and support for over 140 languages. The model uses a hy...

Params

14.4 B

Context

—

Downloads 30d

1.5 M

Likes

126

Commercial use: allowed apache-2.0 Not gated SAFETENSORS View on Hugging Face ↗

Download history

daily snapshots · 10 days

1.5 M1.2 M

Jul 28Jul 31Aug 3Aug 6

Can you run it?

Estimated VRAM at 8K context unless noted. Pick your hardware to see the verdict per quantization.

File	Quant	Size	Est. VRAM	Verdict on RTX 4090 · 24 GB
model.safetensors	u8	18.8 GB	23.3 GB	⚠️ Tight — reduce context

Estimate: file size × 1.1 + KV cache at 8K + 0.5 GB overhead. Not a benchmark — how we calculate this.

Run it

copy-paste, exact tags checked against the Hub

~ · curl · api/v1

$ curl -s https://aimodelscomparison.com/api/v1/models/gemma-4-26b-a4b-nvfp4
{
  "hf_id": "nvidia/Gemma-4-26B-A4B-NVFP4",
  "params_b": 14.39,
  "context_length": null,
  "license": { "id": "apache-2.0", "commercial": "yes" },
  "downloads_30d": 1471741,
  "vram_estimates": [
    { "quant": "u8", "gb": 23.3 }
  ],
  "updated_at": "2026-07-28T18:03:31Z"
}

est. VRAM —on RTX 4090 · 24 GBJSON API →

Specifications

Architecture: Gemma4ForConditionalGeneration
Parameters: 14.4 B
Tensor type: U8
Licence: apache-2.0
First seen on the Hub: 2026-05-01
Base model: gemma-4-26B-A4B-it
Training datasets: undisclosed
Added to our catalog: 2026-07-28

Family

Base model and the most-downloaded derivatives in the catalog.

Base gemma-4-26B-A4B-it google 11.7 M

Compare with

Qwen3-8B 16.3 M Qwen2.5-7B-Instruct 12.1 M Qwen3.6-35B-A3B-NVFP4 11.3 M gpt-oss-20b 8.6 M Qwen3-32B 8.3 M Llama-3.1-8B-Instruct 8.0 M

Appears in

Best open coding models Commercial-use text models Models that fit in 12 GB