0.60B Qwen3 scale
Captured config identifies Qwen3ForCausalLM and Safetensors metadata reports 596049920 parameters.
Open Source Model Profile · Jackrong
Qwen3-0.6B-Thinking
Qwen3-0.6B-Thinking is a 0.60B-parameter Qwen3-family text-generation fine-tune from Jackrong. Its model card names an Unsloth 4-bit Qwen3 base and Unsloth plus TRL training.
- Publisher
- Jackrong
- Task
- text-generation
- Model type
- qwen3
- License
- apache-2.0
- Library
- transformers
- Publication status
- Accepted · not indexed
Model overview
Qwen3-0.6B-Thinking is published by Jackrong as a Qwen3-based text-generation model. The captured configuration identifies Qwen3ForCausalLM with a qwen3 model type, and Safetensors metadata reports 596049920 parameters. According to the model card, it was fine-tuned from unsloth/qwen3-0.6b-unsloth-bnb-4bit.
Recorded capabilities
Documented Unsloth base
According to the model card, the model was fine-tuned from unsloth/qwen3-0.6b-unsloth-bnb-4bit.
Unsloth plus TRL note
The model card says this Qwen3 model was trained 2x faster with Unsloth and Hugging Face's TRL library.
Use cases in the source record
- Small-model conversational text-generation experiments using the Transformers stack.
Limitations and unknowns
- No evaluation results were extracted from this record.
- No context-window value was extracted from this record.
- The single-claim model card gives no dataset, schedule, or hardware detail beyond the Unsloth and TRL note.
- Provider state is historical snapshot data, not independently refreshed current availability.
Source and provenance
Source: Jackrong/Qwen3-0.6B-Thinking
Captured: Unknown. Processed: 2026-09-07T19:35:40.058404+00:00.
Uploaded finetuned model Developed by: Jackrong License: apache-2.0 Finetuned from model : unsloth/qwen3-0.6b-unsloth-bnb-4bit This qwen3 model was trained 2x faster with Unsloth and Huggingface's TRL library.
F001F002F003F004F005F006F007F008F009F010F011