GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
izambasiron
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
izambasiron
Model Tree
unsloth/Qwen3-0.6B
Input Modalities
Output Modalities
Supported Functionality
| Base model | unsloth/Qwen3-0.6B |
| Parameters | 0.6B |
| Fine-tuning | QLoRA (4-bit) |
| Training data | 168 curated examples |
| Eval data | 42 held-out examples |
| Epochs | 3 |
| Precision | fp16 |
| VRAM (training) | ~6 GB (T4) |
python
from transformers import AutoModelForCausalLM, AutoTokenizer model = AutoModelForCausalLM.from_pretrained( "izambasiron/qwen3-0.6b-markdown-review", torch_dtype=torch.float16, device_map="auto")tokenizer = AutoTokenizer.from_pretrained("izambasiron/qwen3-0.6b-markdown-review") messages = [ {"role": "system", "content": "You are a Markdown document reviewer..."}, {"role": "user", "content": "# My Doc\n\n"}]inputs = tokenizer.apply_chat_template(messages, return_tensors="pt").to(model.device)outputs = model.generate(inputs, max_new_tokens=256)print(tokenizer.decode(outputs[0], skip_special_tokens=True))Download qwen3-0.6b.Q4_K_M.gguf and use with the included Modelfile:
bash
ollama create qwen3-markdown-review -f Modelfileollama run qwen3-markdown-reviewOr directly with llama.cpp:
bash
llama-cli -m qwen3-0.6b.Q4_K_M.gguf -p "<system prompt>" -f input.mdFine-tuned with Unsloth using the notebook at colab_finetune_qwen3_clean.ipynb.
from transformers import AutoModelForCausalLM, AutoTokenizer model = AutoModelForCausalLM.from_pretrained( "izambasiron/qwen3-0.6b-markdown-review", torch_dtype=torch.float16, device_map="auto")tokenizer = AutoTokenizer.from_pretrained("izambasiron/qwen3-0.6b-markdown-review") messages = [ {"role": "system", "content": "You are a Markdown document reviewer..."}, {"role": "user", "content": "# My Doc\n\n"}]inputs = tokenizer.apply_chat_template(messages, return_tensors="pt").to(model.device)outputs = model.generate(inputs, max_new_tokens=256)print(tokenizer.decode(outputs[0], skip_special_tokens=True))ollama create qwen3-markdown-review -f Modelfileollama run qwen3-markdown-reviewllama-cli -m qwen3-0.6b.Q4_K_M.gguf -p "<system prompt>" -f input.md