GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
alphaedge-ai
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
alphaedge-ai
Model Tree
Input Modalities
Output Modalities
Supported Functionality
| Metric | Original | Trimmed | Reduction |
|---|---|---|---|
| Vocabulary size | 248,320 tokens | 32,768 tokens | 86.80% |
| Model size | 4,539,265,536 params | 3,987,452,416 params | 12.16% |
python
from transformers import AutoModelForCausalLM, AutoTokenizer model_name = "alphaedge-ai/Qwen.5-4B-bos-32768" # load the tokenizer and the modeltokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)model = AutoModelForCausalLM.from_pretrained( model_name, torch_dtype="auto", device_map="auto", trust_remote_code=True) # prepare the model inputprompt = "Your prompt in Bosnian."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) # conduct text completiongenerated_ids = model.generate( **model_inputs, max_new_tokens=32768)output_ids = generated_ids[0][len(model_inputs.input_ids[0]):]content = tokenizer.decode(output_ids, skip_special_tokens=True) print("content:", content)text
@misc{qwen3.5, title = {Qwen3.5: Towards Native Multimodal Agents}, author = {Qwen Team}, month = {February}, year = {2026}, url = {https://qwen.ai/blog?id=qwen3.5}}text
@misc{hf_blogpost_trimming, title={Introduction to Trimming}, author={Loïck BOURDOIS and Tom AARSEN and Bram VANROY and Christopher AKIKI and Woojun JUNG and Manuel ROMERO and Prithiv SAKTHI}, year={2026}, url={https://huggingface.co/blog/lbourdois/introduction-to-trimming}, }@misc{qwen3.5, title = {Qwen3.5: Towards Native Multimodal Agents}, author = {Qwen Team}, month = {February}, year = {2026}, url = {https://qwen.ai/blog?id=qwen3.5}}@misc{hf_blogpost_trimming, title={Introduction to Trimming}, author={Loïck BOURDOIS and Tom AARSEN and Bram VANROY and Christopher AKIKI and Woojun JUNG and Manuel ROMERO and Prithiv SAKTHI}, year={2026}, url={https://huggingface.co/blog/lbourdois/introduction-to-trimming}, }from transformers import AutoModelForCausalLM, AutoTokenizer model_name = "alphaedge-ai/Qwen.5-4B-bos-32768" # load the tokenizer and the modeltokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)model = AutoModelForCausalLM.from_pretrained( model_name, torch_dtype="auto", device_map="auto", trust_remote_code=True) # prepare the model inputprompt = "Your prompt in Bosnian."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) # conduct text completiongenerated_ids = model.generate( **model_inputs, max_new_tokens=32768)output_ids = generated_ids[0][len(model_inputs.input_ids[0]):]content = tokenizer.decode(output_ids, skip_special_tokens=True) print("content:", content)