GLM-5.2 is live. #1 throughput on OpenRouter, pay-per-token on FriendliAI. Try it today ➜
CyberNative-AI
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
CyberNative-AI
Model Tree
Base
unsloth/Qwen3.6-35B-A3B
Adapter
this model
Input Modalities
Text
Image
Video
Output Modalities
Text
Supported Functionality
Dedicated Endpoints
unsloth/Qwen3.6-35B-A3B
qwen36_35b_a3b_h200_official_bf16_lora64_24k_20260612/lora_adapter
24576bfloat16python
import torchfrom unsloth import FastLanguageModelmodel, tokenizer = FastLanguageModel.from_pretrained(model_name="CyberNative-AI/Qwen36_35B_A3B_CyberNative_20260612_H200_bf16LoRA64_24k_LoRA",max_seq_length=24576,dtype=torch.bfloat16,load_in_4bit=False,token="hf_...",)
python
model.save_pretrained_merged("merged_bf16",tokenizer,save_method="merged_16bit",)
python
model.push_to_hub_merged("CyberNative-AI/YOUR_MERGED_REPO_NAME",tokenizer,save_method="merged_16bit",token="hf_...",)
python
import torchfrom transformers import AutoModelForCausalLM, AutoTokenizerfrom peft import PeftModelbase = AutoModelForCausalLM.from_pretrained("unsloth/Qwen3.6-35B-A3B",torch_dtype=torch.bfloat16,device_map="auto",trust_remote_code=True,)tok = AutoTokenizer.from_pretrained("unsloth/Qwen3.6-35B-A3B",trust_remote_code=True,)model = PeftModel.from_pretrained(base, "CyberNative-AI/Qwen36_35B_A3B_CyberNative_20260612_H200_bf16LoRA64_24k_LoRA")model = model.merge_and_unload()model.save_pretrained("merged_bf16",safe_serialization=True,max_shard_size="4GB",)tok.save_pretrained("merged_bf16")
If Unsloth merge prints warnings like:
MoE merge fallbackbase weight is being written throughmerged checkpoint will be missing this deltado not trust that merged checkpoint. Use the PEFT merge route or update Unsloth/Unsloth Zoo and retry.