GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
spade-rl
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Run this model inference with full control and performance in your environment.
Model Details
Model Provider
spade-rl
Model Tree
Qwen/Qwen3-8B
Input Modalities
Output Modalities
Supported Functionality
We advise you to use the latest version of transformers.
python
from transformers import AutoModelForCausalLM, AutoTokenizermodel_name = "spade-rl/SPADE-Qwen3-8B-Games"tokenizer = AutoTokenizer.from_pretrained(model_name)model = AutoModelForCausalLM.from_pretrained(model_name,torch_dtype="auto",device_map="auto")prompt = "Give me a short introduction to large language model."messages = [{"role": "user", "content": prompt}]text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)model_inputs = tokenizer([text], return_tensors="pt").to(model.device)generated_ids = model.generate(**model_inputs, max_new_tokens=16384)output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist()print(tokenizer.decode(output_ids, skip_special_tokens=True))
For deployment, you can use sglang>=0.4.6.post1 or vllm>=0.8.5 to create an
OpenAI-compatible API endpoint:
shell
python -m sglang.launch_server --model-path spade-rl/SPADE-Qwen3-8B-Games --context-length 32768
shell
vllm serve spade-rl/SPADE-Qwen3-8B-Games --max-model-len 32768
Note: If you encounter out-of-memory (OOM) issues, consider reducing the context length to a shorter value.
We recommend temperature=0.6, top_p=0.95, top_k=20, min_p=0, following
the sampling guidance on the base model card.