Store › model › LLM

Qwen3-0.6B-GGUF

Name: Qwen3-0.6B-GGUF
Author: unsloth

by unsloth · source Hugging Face · updated 2025-06-23

apache-2.0378 MB~1 GB RAMsource aliveunlabeled

See our collection for all versions of Qwen3 including GGUF, 4-bit & 16-bit formats. Learn to run Qwen3 correctly - Read our Guide.

Add to LogiShell Open in the web IDE

The button opens LogiShell with this card; nothing installs from a link by itself. Inside the app the install goes through lsh models install hf:unsloth/Qwen3-0.6B-GGUF and its progress lives in the Resource Center.

Source and license

Source: https://huggingface.co/unsloth/Qwen3-0.6B-GGUF
License: apache-2.0 · text
Requirements: about 1 GB of RAM, 378 MB on disk (estimate: suggested file size × 1.15 + 0.5 GB; a real measurement comes with lsh models). Runs with llama.cpp, ollama.
Tags: transformers gguf qwen3 text-generation qwen unsloth en endpoints_compatible conversational

Numbers

118,197 downloads on Hugging Face
141 likes
license apache-2.0
0.4 GB for Qwen3-0.6B-Q4_K_M.gguf
27,665 stars on QwenLM/Qwen3
68 open issues and PRs
327,838 npm downloads a week for node-llama-cpp
latest node-llama-cpp@3.22.1

Numbers as of 2026-10-02 20:54 UTC, from the source API.

Summary

Summary not ready yet: the numbers are here, the text is not. It is written by the collector through the LogiShell model facade when a provider key is present.

Reviews

No reviews yet. Reviews are written inside LogiShell: open this card in the app.

Files

file	quant	size
`Qwen3-0.6B-BF16.gguf`	BF16	1.1 GB
`Qwen3-0.6B-IQ4_NL.gguf`	IQ4_NL	364 MB
`Qwen3-0.6B-IQ4_XS.gguf`	IQ4_XS	351 MB
`Qwen3-0.6B-Q2_K.gguf`	Q2_K	283 MB
`Qwen3-0.6B-Q2_K_L.gguf`	Q2_K_L	283 MB
`Qwen3-0.6B-Q3_K_M.gguf`	Q3_K_M	331 MB
`Qwen3-0.6B-Q3_K_S.gguf`	Q3_K_S	308 MB
`Qwen3-0.6B-Q4_0.gguf`	Q4_0	364 MB
`Qwen3-0.6B-Q4_1.gguf`	Q4_1	390 MB
`Qwen3-0.6B-Q4_K_M.gguf`	Q4_K_M	378 MB
`Qwen3-0.6B-Q4_K_S.gguf`	Q4_K_S	366 MB
`Qwen3-0.6B-Q5_K_M.gguf`	Q5_K_M	424 MB
`Qwen3-0.6B-Q5_K_S.gguf`	Q5_K_S	416 MB
`Qwen3-0.6B-Q6_K.gguf`	Q6_K	472 MB
`Qwen3-0.6B-Q8_0.gguf`	Q8_0	610 MB
`Qwen3-0.6B-UD-IQ1_M.gguf`	IQ1_M	211 MB
`Qwen3-0.6B-UD-IQ1_S.gguf`	IQ1_S	205 MB
`Qwen3-0.6B-UD-IQ2_M.gguf`	IQ2_M	256 MB
`Qwen3-0.6B-UD-IQ2_XXS.gguf`	IQ2_XXS	223 MB
`Qwen3-0.6B-UD-IQ3_XXS.gguf`	IQ3_XXS	269 MB
`Qwen3-0.6B-UD-Q2_K_XL.gguf`	Q2_K_XL	288 MB
`Qwen3-0.6B-UD-Q3_K_XL.gguf`	Q3_K_XL	340 MB
`Qwen3-0.6B-UD-Q4_K_XL.gguf`	Q4_K_XL	387 MB
`Qwen3-0.6B-UD-Q5_K_XL.gguf`	Q5_K_XL	426 MB
`Qwen3-0.6B-UD-Q6_K_XL.gguf`	Q6_K_XL	550 MB
`Qwen3-0.6B-UD-Q8_K_XL.gguf`	Q8_K_XL	805 MB

From the source README

See our collection for all versions of Qwen3 including GGUF, 4-bit & 16-bit formats.

Learn to run Qwen3 correctly - Read our Guide.

Unsloth Dynamic 2.0 achieves superior accuracy & outperforms other leading quants.

✨ Run & Fine-tune Qwen3 with Unsloth!

Fine-tune Qwen3 (14B) for free using our Google Colab notebook here!
Read our Blog about Qwen3 support: unsloth.ai/blog/qwen3
View the rest of our notebooks in our docs here.
Run & export your fine-tuned model to Ollama, llama.cpp or HF.

| Unsloth supports | Free Notebooks | Performance | Memory use |
|-----------------|--------------------------------------------------------------------------------------------------------------------------|-------------|----------|
| Qwen3 (14B) | ▶️ Start on Colab | 3x faster | 70% less |
| GRPO with Qwen3 (8B) | ▶️ Start on Colab | 3x faster | 80% less |
| Llama-3.2 (3B) | ▶️ Start on Colab-Conversational.ipynb) | 2.4x faster | 58% less |
| Llama-3.2 (11B vision) | ▶️ Start on Colab-Vision.ipynb) | 2x faster | 60% less |
| Qwen2.5 (7B) | ▶️ Start on Colab-Alpaca.ipynb) | 2x faster | 60% less |
| **P…

Source: https://huggingface.co/unsloth/Qwen3-0.6B-GGUF

Card id model:hf:unsloth/Qwen3-0.6B-GGUF · collected 2026-10-02 20:54 UTC · JSON