Instructions to use bahadirakdemir/gemma-4-12B-it-assistant-fp8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use bahadirakdemir/gemma-4-12B-it-assistant-fp8 with Transformers:

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

pipe = pipeline("text-generation", model="bahadirakdemir/gemma-4-12B-it-assistant-fp8")

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("bahadirakdemir/gemma-4-12B-it-assistant-fp8")
model = AutoModelForMultimodalLM.from_pretrained("bahadirakdemir/gemma-4-12B-it-assistant-fp8")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use bahadirakdemir/gemma-4-12B-it-assistant-fp8 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "bahadirakdemir/gemma-4-12B-it-assistant-fp8"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "bahadirakdemir/gemma-4-12B-it-assistant-fp8",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/bahadirakdemir/gemma-4-12B-it-assistant-fp8

SGLang

How to use bahadirakdemir/gemma-4-12B-it-assistant-fp8 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 "bahadirakdemir/gemma-4-12B-it-assistant-fp8" \
    --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": "bahadirakdemir/gemma-4-12B-it-assistant-fp8",
		"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 "bahadirakdemir/gemma-4-12B-it-assistant-fp8" \
        --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": "bahadirakdemir/gemma-4-12B-it-assistant-fp8",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use bahadirakdemir/gemma-4-12B-it-assistant-fp8 with Docker Model Runner:
```
docker model run hf.co/bahadirakdemir/gemma-4-12B-it-assistant-fp8
```

Gemma 4 12B-it Assistant — FP8 (ModelOpt)

FP8-quantized version of google/gemma-4-12B-it-assistant, the Multi-Token Prediction (MTP) drafter that pairs with the Gemma 4 12B-it target for speculative decoding. The drafter is a small 4-layer model; its linear layers are quantized to FP8 (E4M3) with per-tensor static scales via NVIDIA ModelOpt. The drafter↔target handshake projections (pre_projection, post_projection) and lm_head stay in BF16.

This drafter is not a standalone text model — it requires a target model to provide shared_kv_states at inference time. Use it as a spec model in vLLM, paired with the 12B-it target.

Compatible target

Pairs with bahadirakdemir/gemma-4-12B-it-text-fp8 — the FP8-quantized 12B-it text tower produced by the same pipeline. The FP8 scales were calibrated by running real speculative decoding against the 12B-it target over 32 instruct-style prompts.

Requirements

This drafter and its target use the unified Gemma 4 architecture (gemma4_unified), which is newer than the classic gemma4 (e.g. 31B). You need:

transformers ≥ 5.10.0
vLLM with gemma4_unified support — at the time of writing this is on the main branch / nightly (uv pip install -U vllm --pre), not yet in a tagged stable release (≤ 0.22.0). It will be in the next stable release.

Usage with vLLM

vllm serve bahadirakdemir/gemma-4-12B-it-text-fp8 \
  --quantization modelopt \
  --max-model-len 8192 \
  --max-num-batched-tokens 8192 \
  --gpu-memory-utilization 0.5 \
  --limit-mm-per-prompt '{"image": 0, "audio": 0}' \
  --speculative-config '{"model": "bahadirakdemir/gemma-4-12B-it-assistant-fp8", "num_speculative_tokens": 4}'

Tested with vllm/vllm-openai:gemma4-0505-arm64-cu130 on NVIDIA GB10.

This is the 12B counterpart of bahadirakdemir/gemma-4-31B-it-assistant-fp8, produced by the same pipeline.

License: Apache 2.0, inherited from upstream Gemma 4 — see the Gemma 4 license.

Downloads last month: 157

Safetensors

Model size

0.4B params

Tensor type

BF16

F8_E4M3

Model tree for bahadirakdemir/gemma-4-12B-it-assistant-fp8

Base model

google/gemma-4-12B-it-assistant

Quantized

(13)

this model