Store › model › LLM
Qwen3-Coder-30B-A3B-Instruct-GGUF
by unsloth · source Hugging Face · updated 2026-01-30
apache-2.017 GB~21 GB RAMsource aliveunlabeled
See our collection for all versions of Qwen3 including GGUF, 4-bit & 16-bit formats. Learn to run Qwen3-Coder 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-Coder-30B-A3B-Instruct-GGUF and its progress lives in the Resource Center.
Source and license
- Source: https://huggingface.co/unsloth/Qwen3-Coder-30B-A3B-Instruct-GGUF
- License: apache-2.0 · text
- Requirements: about 21 GB of RAM, 17 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:
transformersggufunslothqwen3qwentext-generationendpoints_compatibleimatrixconversational
Numbers
- 8,649,679 downloads on Hugging Face
- 1,099 likes
- license apache-2.0
- 17 GB for Qwen3-Coder-30B-A3B-Instruct-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 |
|---|---|---|
BF16/Qwen3-Coder-30B-A3B-Instruct-BF16-00001-of-00002.gguf | BF16 | 46 GB |
BF16/Qwen3-Coder-30B-A3B-Instruct-BF16-00002-of-00002.gguf | BF16 | 11 GB |
Qwen3-Coder-30B-A3B-Instruct-IQ4_NL.gguf | IQ4_NL | 16 GB |
Qwen3-Coder-30B-A3B-Instruct-IQ4_XS.gguf | IQ4_XS | 15 GB |
Qwen3-Coder-30B-A3B-Instruct-Q2_K.gguf | Q2_K | 10 GB |
Qwen3-Coder-30B-A3B-Instruct-Q2_K_L.gguf | Q2_K_L | 11 GB |
Qwen3-Coder-30B-A3B-Instruct-Q3_K_M.gguf | Q3_K_M | 14 GB |
Qwen3-Coder-30B-A3B-Instruct-Q3_K_S.gguf | Q3_K_S | 12 GB |
Qwen3-Coder-30B-A3B-Instruct-Q4_0.gguf | Q4_0 | 16 GB |
Qwen3-Coder-30B-A3B-Instruct-Q4_1.gguf | Q4_1 | 18 GB |
Qwen3-Coder-30B-A3B-Instruct-Q4_K_M.gguf | Q4_K_M | 17 GB |
Qwen3-Coder-30B-A3B-Instruct-Q4_K_S.gguf | Q4_K_S | 16 GB |
Qwen3-Coder-30B-A3B-Instruct-Q5_K_M.gguf | Q5_K_M | 20 GB |
Qwen3-Coder-30B-A3B-Instruct-Q5_K_S.gguf | Q5_K_S | 20 GB |
Qwen3-Coder-30B-A3B-Instruct-Q6_K.gguf | Q6_K | 23 GB |
Qwen3-Coder-30B-A3B-Instruct-Q8_0.gguf | Q8_0 | 30 GB |
Qwen3-Coder-30B-A3B-Instruct-UD-IQ1_M.gguf | IQ1_M | 9.0 GB |
Qwen3-Coder-30B-A3B-Instruct-UD-IQ1_S.gguf | IQ1_S | 8.3 GB |
Qwen3-Coder-30B-A3B-Instruct-UD-IQ2_M.gguf | IQ2_M | 10 GB |
Qwen3-Coder-30B-A3B-Instruct-UD-IQ2_XXS.gguf | IQ2_XXS | 9.6 GB |
Qwen3-Coder-30B-A3B-Instruct-UD-IQ3_XXS.gguf | IQ3_XXS | 12 GB |
Qwen3-Coder-30B-A3B-Instruct-UD-Q2_K_XL.gguf | Q2_K_XL | 11 GB |
Qwen3-Coder-30B-A3B-Instruct-UD-Q3_K_XL.gguf | Q3_K_XL | 13 GB |
Qwen3-Coder-30B-A3B-Instruct-UD-Q4_K_XL.gguf | Q4_K_XL | 16 GB |
Qwen3-Coder-30B-A3B-Instruct-UD-Q5_K_XL.gguf | Q5_K_XL | 20 GB |
Qwen3-Coder-30B-A3B-Instruct-UD-Q6_K_XL.gguf | Q6_K_XL | 25 GB |
Qwen3-Coder-30B-A3B-Instruct-UD-Q8_K_XL.gguf | Q8_K_XL | 34 GB |
Qwen3-Coder-30B-A3B-Instruct-UD-TQ1_0.gguf | TQ1_0 | 7.5 GB |
From the source README
See our collection for all versions of Qwen3 including GGUF, 4-bit & 16-bit formats.
Learn to run Qwen3-Coder correctly - Read our Guide.
See Unsloth Dynamic 2.0 GGUFs for our quantization benchmarks.
✨ Read our Qwen3-Coder Guide here!
- Fine-tune Qwen3 (14B) for free using our Google Colab notebook!
- Read our Blog about Qwen3 support: unsloth.ai/blog/qwen3
- View the rest of our notebooks in our docs here.
- | 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 |
Qwen3-Coder-30B-A3B-Instruct
Highlights
Qwen3-Coder is ava…
Source: https://huggingface.co/unsloth/Qwen3-Coder-30B-A3B-Instruct-GGUF
Card id model:hf:unsloth/Qwen3-Coder-30B-A3B-Instruct-GGUF · collected 2026-10-02 20:54 UTC · JSON