Open-weight model
Qwen3.6-27B-A3B-Coder-ROCMFP4_FAST
by Alston Albarado alst10/Qwen3.6-27B-A3B-Coder-ROCMFP4_FAST
Qwen3.6-27B-A3B-Coder-ROCMFP4_FAST is an open-weight model from Alston Albarado, released under Creative Commons Attribution 4.0. Its published files total 14.0 GB.
This model was dynamically quantized and generated using the ROCmFPX My Repo Space To run this model, you must use the specialized ROCmFPX fork of llama.cpp by charlie12345. Standard llama.cpp releases do not currently support ROCmFPX quantization formats.
Model Card
By Alston Albarado, published under cc-by-4.0, revision 039bc591c74d.
This model was dynamically quantized and generated using the ROCmFPX My Repo Space To run this model, you must use the specialized ROCmFPX fork of llama.cpp by charlie12345. Standard llama.cpp releases do not currently support ROCmFPX quantization formats. This model is distributed under the Creative Commons Attribution 4.0 International (CC BY 4.0) license. Please adhere to the original license constraints of the base model and provide appropriate attribution when sharing.
Read Alston Albarado's full model card
Qwen3.6-27B-A3B-Coder-ROCMFP4_FAST - ROCmFPX Quantized
This model was dynamically quantized and generated using the ROCmFPX My Repo Space * Original Base Model: ManniX-ITA/Qwen3.6-27B-A3B-Coder
Usage Instructions with ROCmFPX llama.cpp
To run this model, you must use the specialized ROCmFPX fork of llama.cpp by charlie12345. Standard llama.cpp releases do not currently support ROCmFPX quantization formats.
# 1. Clone the ROCmFPX repository
git clone --depth 1 [https://github.com/charlie12345/ROCmFPX.git](https://github.com/charlie12345/ROCmFPX.git)
cd ROCmFPX
# 2. Build the project
cmake -B build -G Ninja -DGGML_CUDA=OFF -DGGML_NATIVE=OFF
cmake --build build --target llama-cli -j
# 3. Run the model
./build/bin/llama-cli -m Qwen3.6-27B-A3B-Coder-Q4_0_ROCMFP4_FAST.gguf -p "You are a helpful assistant. Hello!" -n 128
License
This model is distributed under the Creative Commons Attribution 4.0 International (CC BY 4.0) license. Please adhere to the original license constraints of the base model and provide appropriate attribution when sharing.
Identity and Version
- Repository
- alst10/Qwen3.6-27B-A3B-Coder-ROCMFP4_FAST
- Publisher
- Alston Albarado
- Task
- Not stated by the source
- Modality
- Other
- Library
- Not stated by the source
- Parameters
- Not stated by the source
- Languages
- amd
- Revision
- 039bc591c74d7fb9392a87fb43edf8953a50ac42
- First published
- 2026-09-23
- Last updated
- 2026-09-23
Files and Weights
3 files, 14.0 GB in total. The weights are 1 file totalling 14.0 GB in gguf.
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| Qwen3.6-27B-A3B-Coder-Q4_0_ROCMFP4_FAST.gguf | Weights | 14.0 GB | 709a0d942038 |
| README.md | Documentation | 1.4 KB | — |
| .gitattributes | Repository | 1.6 KB | — |
License and Download
- License
- cc-by-4.0
- Access
- Open weights, no gate
- Download size
- 14.0 GB
Released by Alston Albarado through its official repository on Hugging Face. Read the license.
Built From
- Derived from ManniX-ITA/Qwen3.6-27B-A3B-Coder
- Quantized from ManniX-ITA/Qwen3.6-27B-A3B-Coder
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 14.0 GB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.
Questions About Qwen3.6-27B-A3B-Coder-ROCMFP4_FAST
Can I use Qwen3.6-27B-A3B-Coder-ROCMFP4_FAST commercially?
Yes. Qwen3.6-27B-A3B-Coder-ROCMFP4_FAST is released under Creative Commons Attribution 4.0. CC BY 4.0 permits sharing and adapting the work, including commercially, provided the creator is credited and changes are indicated.