Instructions to use xv0y5ncu/Gemma-4-E4B-it-GLQ-3.5bpw-mix3-8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use xv0y5ncu/Gemma-4-E4B-it-GLQ-3.5bpw-mix3-8 with Transformers:

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

pipe = pipeline("image-text-to-text", model="xv0y5ncu/Gemma-4-E4B-it-GLQ-3.5bpw-mix3-8")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("xv0y5ncu/Gemma-4-E4B-it-GLQ-3.5bpw-mix3-8")
model = AutoModelForMultimodalLM.from_pretrained("xv0y5ncu/Gemma-4-E4B-it-GLQ-3.5bpw-mix3-8", device_map="auto")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use xv0y5ncu/Gemma-4-E4B-it-GLQ-3.5bpw-mix3-8 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "xv0y5ncu/Gemma-4-E4B-it-GLQ-3.5bpw-mix3-8"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "xv0y5ncu/Gemma-4-E4B-it-GLQ-3.5bpw-mix3-8",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/xv0y5ncu/Gemma-4-E4B-it-GLQ-3.5bpw-mix3-8

SGLang

How to use xv0y5ncu/Gemma-4-E4B-it-GLQ-3.5bpw-mix3-8 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 "xv0y5ncu/Gemma-4-E4B-it-GLQ-3.5bpw-mix3-8" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "xv0y5ncu/Gemma-4-E4B-it-GLQ-3.5bpw-mix3-8",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

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 "xv0y5ncu/Gemma-4-E4B-it-GLQ-3.5bpw-mix3-8" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "xv0y5ncu/Gemma-4-E4B-it-GLQ-3.5bpw-mix3-8",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Docker Model Runner
How to use xv0y5ncu/Gemma-4-E4B-it-GLQ-3.5bpw-mix3-8 with Docker Model Runner:
```
docker model run hf.co/xv0y5ncu/Gemma-4-E4B-it-GLQ-3.5bpw-mix3-8
```

Gemma-4-E4B-it — GLQ 3.5 bpw (mixed 3–8)

GLQ (Golay–Leech Quantization) of google/gemma-4-E4B-it at 3.5 bpw param-weighted average, with sensitivity-driven mixed precision over the range 3–8 bpw. Layers are ranked by proxy loss; the most sensitive ones (typically k_proj, o_proj, per_layer_input_gate) get more bits; the bulk MLP layers (gate_proj, up_proj, down_proj) get 3 bpw.

Quick start

pip install glq "transformers>=5.13.1,<5.15"

Pin transformers below 5.15 — 5.15.0 moved gemma-4 to a per-layer config, so config.head_dim raises and vLLM dies before loading a single weight. Verified on 5.14.1 with vLLM 0.27.1. Not specific to GLQ: stock bf16 gemma-4 fails the same way.

import glq.hf_integration  # registers the GLQ quantization config
from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained(
    "xv0y5ncu/Gemma-4-E4B-it-GLQ-3.5bpw-mix3-8",
    torch_dtype="bfloat16",
    device_map="cuda",
)
tokenizer = AutoTokenizer.from_pretrained("xv0y5ncu/Gemma-4-E4B-it-GLQ-3.5bpw-mix3-8")

vLLM (pip install vllm + pip install glq):

vllm serve xv0y5ncu/Gemma-4-E4B-it-GLQ-3.5bpw-mix3-8 --quantization glq

Quality vs other 3-bpw-class quants

mmlu_pro at 2% sample (n = 247), all generation with enable_thinking=true:

Variant	bpw (param-weighted)	acc	stderr	engine	vs bf16
bf16	16.0	0.6640	0.0289	vLLM	100%
GLQ 3.5 mix 3–8 (this model)	3.50	0.5628	0.0310	vLLM	84.8%
GGUF Q3_K_S	3.89	0.4696	0.0300	llama.cpp	70.7%
GGUF UD-IQ3_XXS (calibrated)	3.75	0.4818	0.0295	llama.cpp	72.6%
GLQ uniform 3.0	3.00	0.4413	0.0311	vLLM	66.5%

At 3.5 bpw — lower than both GGUF Q3 variants — GLQ outperforms them by ~9pp thanks to sensitivity-driven bit allocation.

Bit allocation summary

Total quantized weights: 3,945,267,200
   3 bpw: 113 sublayers (2,941,255,680 weights, 74.6%)  — mostly mlp.{gate,up,down}_proj
   4 bpw:  41 sublayers (  525,598,720 weights, 13.3%)
   5 bpw:  35 sublayers (  200,540,160 weights,  5.1%)
   6 bpw:  32 sublayers (  110,755,840 weights,  2.8%)
   7 bpw:  72 sublayers (  121,896,960 weights,  3.1%)
   8 bpw:  49 sublayers (   45,219,840 weights,  1.1%)  — most sensitive: k_proj, per_layer_*

PLE embedding: 4 bpw (separate)
embed_tokens, lm_head, norms: bf16
Average SQNR: 21.77 dB

Quantization details

Method: E8 lattice codebook (65 536 entries) + RHT (random Hadamard transform) + LDLQ optimal rounding, with a 256-entry second-stage codebook for residual quantization (RVQ).
Calibration: 128 samples × 2048 tokens from C4.
Allocator: greedy marginal-gain over per-layer proxy losses, profiled at 3–8 bpw.
Quantizer: glq.quantize_model.
Hardware: NVIDIA RTX PRO 6000 Blackwell, 96 GB VRAM. Total quantization wall time: ~8 min (profile + allocate + quantize).

License

License: Apache 2.0 — see https://ai.google.dev/gemma/docs/gemma_4_license

Original model: https://huggingface.co/google/gemma-4-E4B-it

Derivative quantization work; the base Gemma 4 model and the GLQ tooling (https://github.com/cnygaard/glq) are both Apache 2.0. Quantizing the weights does not change the license.

🔗 GLQ on GitHub: https://github.com/cnygaard/glq — if you like it, a ⭐ is appreciated.