Alibaba Qwen3 updated 4B instruct model. 256K native context, Apache 2.0. Optimized for instruction-following, tool-calling, and agentic workflows without CoT overhead.
Alibaba Qwen3.5 sub-1B via Unsloth Dynamic 2.0. 256K context, Apache 2.0. Optimized for lightweight function-calling agents and document parsing workflows.
Alibaba Qwen3.5 2B edge-optimized model. Hybrid Gated DeltaNet+Attention architecture, 256K context, Apache 2.0. Built for tool-calling agents and multimodal workflows.
unsloth/Qwen3-Coder-7B-GGUF
OpenClaw-recommended coding specialist. 7B params, 128K context, Apache 2.0. Optimized for tool-calling, shell commands, and multi-file edits in agentic workflows.
To get started, install the `transformers` library:
pip install transformersThen, use the following snippet to load the model:
from transformers import AutoTokenizer, AutoModelForCausalLM
model_id = "unsloth/Qwen3-Coder-7B-GGUF"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id)
# Your inference code here...Qwen3-72B-Coder
Knowledge Distillation (Logits)
Flickr30k (Conceptual)
Multimodal Generation
| Metric | Student Model | Teacher Model |
|---|---|---|
| Model Size | 5.2GB | 8.5GB |
| BLEU Score | 28.5 | 30.1 |