Store › model › LLM
Qwen3-4B-GGUF
by unsloth · source Hugging Face · updated 2025-06-08
apache-2.02.3 GB~4 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/Qwen3-4B-GGUF and its progress lives in the Resource Center.
Source and license
- Source: https://huggingface.co/unsloth/Qwen3-4B-GGUF
- License: apache-2.0 · text
- Requirements: about 4 GB of RAM, 2.3 GB on disk (estimate: suggested file size × 1.15 + 0.5 GB; a real measurement comes with lsh models). Runs with llama.cpp, ollama.
- Tags:
transformersggufqwen3text-generationqwenunslothenendpoints_compatibleconversational
Numbers
- 442,310 downloads on Hugging Face
- 246 likes
- license apache-2.0
- 2.3 GB for Qwen3-4B-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 20:53 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 |
|---|---|---|
Qwen3-4B-BF16.gguf | BF16 | 7.5 GB |
Qwen3-4B-IQ4_NL.gguf | IQ4_NL | 2.2 GB |
Qwen3-4B-IQ4_XS.gguf | IQ4_XS | 2.1 GB |
Qwen3-4B-Q2_K.gguf | Q2_K | 1.6 GB |
Qwen3-4B-Q2_K_L.gguf | Q2_K_L | 1.6 GB |
Qwen3-4B-Q3_K_M.gguf | Q3_K_M | 1.9 GB |
Qwen3-4B-Q3_K_S.gguf | Q3_K_S | 1.8 GB |
Qwen3-4B-Q4_0.gguf | Q4_0 | 2.2 GB |
Qwen3-4B-Q4_1.gguf | Q4_1 | 2.4 GB |
Qwen3-4B-Q4_K_M.gguf | Q4_K_M | 2.3 GB |
Qwen3-4B-Q4_K_S.gguf | Q4_K_S | 2.2 GB |
Qwen3-4B-Q5_K_M.gguf | Q5_K_M | 2.7 GB |
Qwen3-4B-Q5_K_S.gguf | Q5_K_S | 2.6 GB |
Qwen3-4B-Q6_K.gguf | Q6_K | 3.1 GB |
Qwen3-4B-Q8_0.gguf | Q8_0 | 4.0 GB |
Qwen3-4B-UD-IQ1_M.gguf | IQ1_M | 1.1 GB |
Qwen3-4B-UD-IQ1_S.gguf | IQ1_S | 1.0 GB |
Qwen3-4B-UD-IQ2_M.gguf | IQ2_M | 1.4 GB |
Qwen3-4B-UD-IQ2_XXS.gguf | IQ2_XXS | 1.2 GB |
Qwen3-4B-UD-IQ3_XXS.gguf | IQ3_XXS | 1.6 GB |
Qwen3-4B-UD-Q2_K_XL.gguf | Q2_K_XL | 1.6 GB |
Qwen3-4B-UD-Q3_K_XL.gguf | Q3_K_XL | 2.0 GB |
Qwen3-4B-UD-Q4_K_XL.gguf | Q4_K_XL | 2.4 GB |
Qwen3-4B-UD-Q5_K_XL.gguf | Q5_K_XL | 2.7 GB |
Qwen3-4B-UD-Q6_K_XL.gguf | Q6_K_XL | 3.4 GB |
Qwen3-4B-UD-Q8_K_XL.gguf | Q8_K_XL | 4.7 GB |
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 |
| **Phi…
Source: https://huggingface.co/unsloth/Qwen3-4B-GGUF
Card id model:hf:unsloth/Qwen3-4B-GGUF · collected 2026-10-02 20:53 UTC · JSON