GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
kiel2
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
kiel2
Model Tree
Qwen/Qwen3-VL-4B-Instruct
Input Modalities
Output Modalities
Supported Functionality
4bit/ — Pre-quantized 4-bit weights (ideal for lower VRAM setups like a Tesla T4 or consumer GPUs).16bit/ — Full-precision 16-bit weights (ideal for high-VRAM training/inference).adapter_model.safetensors), tokenizer configuration, and chat template.You can easily load either version directly using Hugging Face transformers by specifying the appropriate subfolder:
python
import torchfrom transformers import AutoModelForVision2Seq, AutoProcessor model_id = "kiel2/kiel-2-codex" print("Loading Kiel-2-Codex (4-bit)...")model = AutoModelForVision2Seq.from_pretrained( model_id, subfolder="4bit", torch_dtype=torch.float16, device_map="auto")processor = AutoProcessor.from_pretrained(model_id)Python
import torchfrom transformers import AutoModelForVision2Seq, AutoProcessor model_id = "kiel2/kiel-2-codex" print("Loading Kiel-2-Codex (16-bit)...")model = AutoModelForVision2Seq.from_pretrained( model_id, subfolder="16bit", torch_dtype=torch.bfloat16 if torch.cuda.is_bf16_supported() else torch.float16, device_map="auto")processor = AutoProcessor.from_pretrained(model_id)Base Model: Qwen/Qwen3-VL-4B-Instruct
Fine-Tuning Framework: Unsloth / Hugging Face TRL & PEFT
Task Focus: Multimodal code generation and structural layout analysis.
This model inherits the licensing structure of its base architecture under the Apache 2.0 License.
import torchfrom transformers import AutoModelForVision2Seq, AutoProcessor model_id = "kiel2/kiel-2-codex" print("Loading Kiel-2-Codex (16-bit)...")model = AutoModelForVision2Seq.from_pretrained( model_id, subfolder="16bit", torch_dtype=torch.bfloat16 if torch.cuda.is_bf16_supported() else torch.float16, device_map="auto")processor = AutoProcessor.from_pretrained(model_id)