GLM-5.2 is live. #1 throughput on OpenRouter, pay-per-token on FriendliAI. Try it today ➜
stenml
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
stenml
Model Tree
google/gemma-4-12B-it
Input Modalities
Output Modalities
Supported Functionality
Install the dependencies:
markdown
pip install -U transformers torch accelerate
Example:
markdown
from transformers import AutoModelForMultimodalLM, AutoProcessormodel_id = "stenml/BowLingual-12B-v1"processor = AutoProcessor.from_pretrained(model_id)model = AutoModelForMultimodalLM.from_pretrained(model_id,dtype="auto",device_map="auto",)messages = [{"role": "user","content": "Translate into natural casual Thai: I'm almost home.",}]inputs = processor.apply_chat_template(messages,tokenize=True,return_dict=True,return_tensors="pt",add_generation_prompt=True,enable_thinking=False,).to(model.device)output = model.generate(**inputs, max_new_tokens=256)generated = output[0][inputs["input_ids"].shape[-1]:]print(processor.decode(generated, skip_special_tokens=True))
1.00.9564Translation applications may benefit from lower-temperature or deterministic decoding, depending on the prompt and desired amount of stylistic variation.
model.safetensors: full model weightstokenizer.json: Gemma 4 tokenizertokenizer_config.json: tokenizer and response parsing metadatachat_template.jinja: canonical Gemma 4 chat templateprocessor_config.json: multimodal processor configurationThe Q4_K_M GGUF release is available at stenml/BowLingual-12B-v1-GGUF.
No formal benchmark results are currently published for this release. Test it against representative conversational messages before production use.
Apache License 2.0, following the Gemma 4 base model metadata.