Instructions to use exolabs/gemma-4-E4B-it-Q4_K_M-dequant-bf16-vllm with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use exolabs/gemma-4-E4B-it-Q4_K_M-dequant-bf16-vllm with Transformers:

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

pipe = pipeline("text-generation", model="exolabs/gemma-4-E4B-it-Q4_K_M-dequant-bf16-vllm")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("exolabs/gemma-4-E4B-it-Q4_K_M-dequant-bf16-vllm")
model = AutoModelForCausalLM.from_pretrained("exolabs/gemma-4-E4B-it-Q4_K_M-dequant-bf16-vllm", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use exolabs/gemma-4-E4B-it-Q4_K_M-dequant-bf16-vllm with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "exolabs/gemma-4-E4B-it-Q4_K_M-dequant-bf16-vllm"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "exolabs/gemma-4-E4B-it-Q4_K_M-dequant-bf16-vllm",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/exolabs/gemma-4-E4B-it-Q4_K_M-dequant-bf16-vllm

SGLang

How to use exolabs/gemma-4-E4B-it-Q4_K_M-dequant-bf16-vllm 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 "exolabs/gemma-4-E4B-it-Q4_K_M-dequant-bf16-vllm" \
    --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": "exolabs/gemma-4-E4B-it-Q4_K_M-dequant-bf16-vllm",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "exolabs/gemma-4-E4B-it-Q4_K_M-dequant-bf16-vllm" \
        --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": "exolabs/gemma-4-E4B-it-Q4_K_M-dequant-bf16-vllm",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use exolabs/gemma-4-E4B-it-Q4_K_M-dequant-bf16-vllm with Docker Model Runner:
```
docker model run hf.co/exolabs/gemma-4-E4B-it-Q4_K_M-dequant-bf16-vllm
```

Configuration Parsing Warning:In config.json: "num_experts" must be a number

Gemma 4 E4B IT Q4_K_M GGUF Dequantized BF16 for vLLM

This private artifact was converted from unsloth/gemma-4-E4B-it-GGUF file gemma-4-E4B-it-Q4_K_M.gguf into standalone Gemma4 text safetensors for Transformers and vLLM.

The converter streams GGUF tensors, dequantizes them to fp32, maps Gemma4 text/PLE tensor names, then casts once to BF16 before writing sharded safetensors. The output config is rewritten from the multimodal gemma4 wrapper to standalone gemma4_text / Gemma4ForCausalLM.

Validation

GGUF dry-run mapping: 720 input tensors; 719 mapped, rope_freqs.weight skipped as runtime metadata.
Output index: 719 HF keys, 5 safetensor shards, 15,036,138,068 bytes.
Transformers load: passed as Gemma4ForCausalLM with tied embeddings and no missing language weights.
Numeric spot-checks: passed with max_abs_vs_bf16=0 for sampled embeddings, PLE projection/norm, layer norms, attention, and layer scalar tensors.
Transformers chat-template generation smoke: passed.
vLLM chat-completions smoke: passed on vLLM 0.23.0.

vLLM command used

VLLM_USE_FLASHINFER_SAMPLER=0 vllm serve /path/to/model   --served-model-name gemma-4-e4b-it-gguf-q4_k_m-bf16   --dtype bfloat16   --max-model-len 4096   --gpu-memory-utilization 0.5   --trust-remote-code

This is an instruction model; use the chat template or /v1/chat/completions for behavioral smoke tests.

Downloads last month: 19

Safetensors

Model size

8B params

Tensor type

BF16

Model tree for exolabs/gemma-4-E4B-it-Q4_K_M-dequant-bf16-vllm

Base model

google/gemma-4-E4B

Finetuned

google/gemma-4-E4B-it

Finetuned

(409)

this model