GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
vishnuOI
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
vishnuOI
Model Tree
Qwen/Qwen3-Coder-30B-A3B-Instruct
Input Modalities
Output Modalities
Supported Functionality
python
from transformers import AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfigfrom peft import PeftModelimport torch base_model_id = "Qwen/Qwen3-Coder-30B-A3B-Instruct"adapter_id = "vishnuOI/unity-coder-30b" bnb_config = BitsAndBytesConfig( load_in_4bit=True, bnb_4bit_quant_type="nf4", bnb_4bit_compute_dtype=torch.bfloat16,) tokenizer = AutoTokenizer.from_pretrained(base_model_id)model = AutoModelForCausalLM.from_pretrained( base_model_id, quantization_config=bnb_config, device_map="auto", torch_dtype=torch.bfloat16,)model = PeftModel.from_pretrained(model, adapter_id)model.eval() messages = [ {"role": "system", "content": "You are an expert Unity game developer."}, {"role": "user", "content": "Write a MonoBehaviour that spawns enemies at random positions."},]text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)inputs = tokenizer(text, return_tensors="pt").to(model.device) with torch.no_grad(): out = model.generate(**inputs, max_new_tokens=512, temperature=0.1, do_sample=True)print(tokenizer.decode(out[0][inputs["input_ids"].shape[1]:], skip_special_tokens=True))from transformers import AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfigfrom peft import PeftModelimport torch base_model_id = "Qwen/Qwen3-Coder-30B-A3B-Instruct"adapter_id = "vishnuOI/unity-coder-30b" bnb_config = BitsAndBytesConfig( load_in_4bit=True, bnb_4bit_quant_type="nf4", bnb_4bit_compute_dtype=torch.bfloat16,) tokenizer = AutoTokenizer.from_pretrained(base_model_id)model = AutoModelForCausalLM.from_pretrained( base_model_id, quantization_config=bnb_config, device_map="auto", torch_dtype=torch.bfloat16,)model = PeftModel.from_pretrained(model, adapter_id)model.eval() messages = [ {"role": "system", "content": "You are an expert Unity game developer."}, {"role": "user", "content": "Write a MonoBehaviour that spawns enemies at random positions."},]text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)inputs = tokenizer(text, return_tensors="pt").to(model.device) with torch.no_grad(): out = model.generate(**inputs, max_new_tokens=512, temperature=0.1, do_sample=True)print(tokenizer.decode(out[0][inputs["input_ids"].shape[1]:], skip_special_tokens=True))