Instructions to use Reza2kn/gemma-4-26B-A4B-it-assistant-NVFP4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Reza2kn/gemma-4-26B-A4B-it-assistant-NVFP4 with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="Reza2kn/gemma-4-26B-A4B-it-assistant-NVFP4")

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("Reza2kn/gemma-4-26B-A4B-it-assistant-NVFP4")
model = AutoModelForMultimodalLM.from_pretrained("Reza2kn/gemma-4-26B-A4B-it-assistant-NVFP4")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Reza2kn/gemma-4-26B-A4B-it-assistant-NVFP4 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Reza2kn/gemma-4-26B-A4B-it-assistant-NVFP4"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Reza2kn/gemma-4-26B-A4B-it-assistant-NVFP4",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Reza2kn/gemma-4-26B-A4B-it-assistant-NVFP4

SGLang

How to use Reza2kn/gemma-4-26B-A4B-it-assistant-NVFP4 with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "Reza2kn/gemma-4-26B-A4B-it-assistant-NVFP4" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Reza2kn/gemma-4-26B-A4B-it-assistant-NVFP4",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "Reza2kn/gemma-4-26B-A4B-it-assistant-NVFP4" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Reza2kn/gemma-4-26B-A4B-it-assistant-NVFP4",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Reza2kn/gemma-4-26B-A4B-it-assistant-NVFP4 with Docker Model Runner:
```
docker model run hf.co/Reza2kn/gemma-4-26B-A4B-it-assistant-NVFP4
```

Gemma 4 26B A4B IT Assistant MTP Draft - NVFP4

NVFP4 quantization of google/gemma-4-26B-A4B-it-assistant, the MTP/draft assistant model.

This is a quantized derivative, not a fine-tune. The repo metadata sets base_model_relation: quantized and tags the base model accordingly.

Format

2D BF16 weight tensors are stored as packed NVFP4 E2M1 codes.
Per-block scales use FP8 E4M3, one scale per 16 values.
1D norm/scalar tensors remain BF16.
The tied embedding/head tensor is quantized; there is no separate lm_head.weight in the source checkpoint.

Because this Gemma 4 assistant architecture currently requires source/newer Transformers support, the repo includes load_gemma4_nvfp4.py, which dequants the packed NVFP4 tensors into the upstream Gemma4AssistantForCausalLM module.

from load_gemma4_nvfp4 import load_model

model, tok = load_model("Reza2kn/gemma-4-26B-A4B-it-assistant-NVFP4", device="cuda")
prompt = "Explain in one sentence what a draft model does."
inputs = tok(prompt, return_tensors="pt").to("cuda")
out = model.generate(**inputs, max_new_tokens=32, do_sample=False)
print(tok.decode(out[0], skip_special_tokens=True))

Files

nvfp4_model.safetensors - packed NVFP4 weights plus BF16 residual tensors.
quantization_config.json - tensor map, block size, parameter counts, and format metadata.
quant_error_report.json - per-tensor relative L2 quantization error.
load_gemma4_nvfp4.py - loader/smoke-test helper.

Notes

This is a storage-format quantization for the new Gemma 4 assistant draft architecture. Native NVFP4 kernel acceleration depends on runtime support catching up to this architecture; the included loader provides a correctness-first dequant path.

Downloads last month: 30

Model tree for Reza2kn/gemma-4-26B-A4B-it-assistant-NVFP4

Base model

google/gemma-4-26B-A4B-it-assistant

Quantized

(9)

this model