GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
satyrn-ai
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
satyrn-ai
Model Tree
unsloth/Qwen3.8-27B
Input Modalities
Output Modalities
Supported Functionality
This model was produced with the Satyrn Models Unsloth training pipeline using the
experiment/py3.15-qwen3.8-27b
configuration.
For this release, the RL dataset stage was disabled (datasets.rl=null).
The full data description and training protocols are available in the repository: https://github.com/satyrn-ai/satyrn-models
Using the Hugging Face CLI:
bash
pip install -U huggingface_hubhf download satyrn-ai/Qwen3.8-27B-py3.15Or from Python:
python
from huggingface_hub import snapshot_download snapshot_download(repo_id="satyrn-ai/Qwen3.8-27B-py3.15")python
from transformers import AutoModelForCausalLM, AutoTokenizer model_id = "satyrn-ai/Qwen3.8-27B-py3.15" tokenizer = AutoTokenizer.from_pretrained(model_id)model = AutoModelForCausalLM.from_pretrained( model_id, dtype="auto", device_map="auto",) messages = [ {"role": "user", "content": "Write a Python function that merges two sorted lists."}] inputs = tokenizer.apply_chat_template( messages, add_generation_prompt=True, return_tensors="pt", return_dict=True,).to(model.device) outputs = model.generate(**inputs, max_new_tokens=4096)print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:], skip_special_tokens=True))Satyrn team
bibtex
@misc{satyrn_qwen38_27b_py315, title = {Qwen3.8-27B-py3.15}, author = {Satyrn team}, year = {2026}, howpublished = {\url{https://huggingface.co/satyrn-ai/Qwen3.8-27B-py3.15}}}pip install -U huggingface_hubhf download satyrn-ai/Qwen3.8-27B-py3.15from huggingface_hub import snapshot_download snapshot_download(repo_id="satyrn-ai/Qwen3.8-27B-py3.15")from transformers import AutoModelForCausalLM, AutoTokenizer model_id = "satyrn-ai/Qwen3.8-27B-py3.15" tokenizer = AutoTokenizer.from_pretrained(model_id)model = AutoModelForCausalLM.from_pretrained( model_id, dtype="auto", device_map="auto",) messages = [ {"role": "user", "content": "Write a Python function that merges two sorted lists."}] inputs = tokenizer.apply_chat_template( messages, add_generation_prompt=True, return_tensors="pt", return_dict=True,).to(model.device) outputs = model.generate(**inputs, max_new_tokens=4096)print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:], skip_special_tokens=True))@misc{satyrn_qwen38_27b_py315, title = {Qwen3.8-27B-py3.15}, author = {Satyrn team}, year = {2026}, howpublished = {\url{https://huggingface.co/satyrn-ai/Qwen3.8-27B-py3.15}}}