DrMoriarty0/Qwen3-Coder-30B-A3B-Instruct-GGUF overview
mAPEX Quantized Models Source Data The source data for quantization was taken from unsloth/Qwen3 Coder 30B A3B Instruct GGUF https://huggingface.co/unsloth/Qwe…
Runs locally from ~7.96 GB disk (8 GB VRAM class GPUs with llama.cpp / guIDE).
Repository Files & Downloads
| File | Type | Quantization | Size | Link |
|---|---|---|---|---|
| Qwen3-Coder-30B-A3B-Instruct-Tier1.gguf | GGUF | GGUF | 27.71 GB | Download |
| Qwen3-Coder-30B-A3B-Instruct-Tier10-s.gguf | GGUF | GGUF | 13.78 GB | Download |
| Qwen3-Coder-30B-A3B-Instruct-Tier10.gguf | GGUF | GGUF | 13.78 GB | Download |
| Qwen3-Coder-30B-A3B-Instruct-Tier11-s.gguf | GGUF | GGUF | 12.02 GB | Download |
| Qwen3-Coder-30B-A3B-Instruct-Tier11.gguf | GGUF | GGUF | 11.94 GB | Download |
| Qwen3-Coder-30B-A3B-Instruct-Tier12-s.gguf | GGUF | GGUF | 11.39 GB | Download |
| Qwen3-Coder-30B-A3B-Instruct-Tier12.gguf | GGUF | GGUF | 11.28 GB | Download |
| Qwen3-Coder-30B-A3B-Instruct-Tier13-s.gguf | GGUF | GGUF | 10.58 GB | Download |
| Qwen3-Coder-30B-A3B-Instruct-Tier13.gguf | GGUF | GGUF | 10.44 GB | Download |
| Qwen3-Coder-30B-A3B-Instruct-Tier14-s.gguf | GGUF | GGUF | 8.65 GB | Download |
| Qwen3-Coder-30B-A3B-Instruct-Tier14.gguf | GGUF | GGUF | 8.80 GB | Download |
| Qwen3-Coder-30B-A3B-Instruct-Tier15-s.gguf | GGUF | GGUF | 7.96 GB | Download |
| Qwen3-Coder-30B-A3B-Instruct-Tier15.gguf | GGUF | GGUF | 8.21 GB | Download |
| Qwen3-Coder-30B-A3B-Instruct-Tier2.gguf | GGUF | GGUF | 25.89 GB | Download |
| Qwen3-Coder-30B-A3B-Instruct-Tier3.gguf | GGUF | GGUF | 23.23 GB | Download |
| Qwen3-Coder-30B-A3B-Instruct-Tier4.gguf | GGUF | GGUF | 21.22 GB | Download |
| Qwen3-Coder-30B-A3B-Instruct-Tier5.gguf | GGUF | GGUF | 19.21 GB | Download |
| Qwen3-Coder-30B-A3B-Instruct-Tier6.gguf | GGUF | GGUF | 18.49 GB | Download |
| Qwen3-Coder-30B-A3B-Instruct-Tier7-s.gguf | GGUF | GGUF | 17.49 GB | Download |
| Qwen3-Coder-30B-A3B-Instruct-Tier7.gguf | GGUF | GGUF | 17.49 GB | Download |
| Qwen3-Coder-30B-A3B-Instruct-Tier8-s.gguf | GGUF | GGUF | 15.44 GB | Download |
| Qwen3-Coder-30B-A3B-Instruct-Tier8.gguf | GGUF | GGUF | 15.44 GB | Download |
| Qwen3-Coder-30B-A3B-Instruct-Tier9-s.gguf | GGUF | GGUF | 14.71 GB | Download |
| Qwen3-Coder-30B-A3B-Instruct-Tier9.gguf | GGUF | GGUF | 14.71 GB | Download |
Model Details
| Model ID | DrMoriarty0/Qwen3-Coder-30B-A3B-Instruct-GGUF |
|---|---|
| Author | DrMoriarty0 |
| Pipeline | — |
| License | apache-2.0 |
| Base model | Qwen/Qwen3-Coder-30B-A3B-Instruct |
| Last modified | 2026-09-25T06:18:07.000Z |
Model README
---
license: apache-2.0
base_model:
- Qwen/Qwen3-Coder-30B-A3B-Instruct
---
mAPEX Quantized Models
Source Data
The source data for quantization was taken from unsloth/Qwen3-Coder-30B-A3B-Instruct-GGUF.
Original source file: BF16/Qwen3-Coder-30B-A3B-Instruct-BF16-00001-of-00002.gguf
Quantization Method
All quants were produced using the modified APEX quantization scheme.
mAPEX (modified Automated Precision EXpert allocation) assigns per-layer, per-tensor precision
for MoE models using llama.cpp's --tensor-type-file.
For more information, see: <https://github.com/DrMoriarty/apex-quant/>
Quantized Models
| Name | Size (GB) | Comments |
|------|-----------|----------|
| tier1 | 27.71 | |
| tier2 | 25.89 | |
| tier3 | 23.23 | |
| tier4 | 21.22 | |
| tier5 | 19.21 | |
| tier6 | 18.49 | |
| tier7 | 17.49 | |
| tier7-s | 17.49 | |
| tier8 | 15.44 | |
| tier8-s | 15.44 | |
| tier9 | 14.71 | |
| tier9-s | 14.71 | |
| tier10 | 13.78 | |
| tier10-s | 13.78 | |
| tier11 | 11.94 | |
| tier11-s | 12.02 | |
| tier12 | 11.28 | |
| tier12-s | 11.39 | |
| tier13 | 10.44 | |
| tier13-s | 10.58 | |
| tier14 | 8.80 | |
| tier14-s | 8.65 | |
| tier15 | 8.21 | |
| tier15-s | 7.96 | |
Run DrMoriarty0/Qwen3-Coder-30B-A3B-Instruct-GGUF with guIDE
Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.
Source: Hugging Face · Compare models