Instructions to use PatrickScully/Qwen3.6-27B-MTP-pi-reasoning-ROCmFP4-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use PatrickScully/Qwen3.6-27B-MTP-pi-reasoning-ROCmFP4-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="PatrickScully/Qwen3.6-27B-MTP-pi-reasoning-ROCmFP4-GGUF",
	filename="Qwen3.6-27B-MTP-pi-reasoning-ROCmFP4-STRIX.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use PatrickScully/Qwen3.6-27B-MTP-pi-reasoning-ROCmFP4-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf PatrickScully/Qwen3.6-27B-MTP-pi-reasoning-ROCmFP4-GGUF
# Run inference directly in the terminal:
llama-cli -hf PatrickScully/Qwen3.6-27B-MTP-pi-reasoning-ROCmFP4-GGUF

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf PatrickScully/Qwen3.6-27B-MTP-pi-reasoning-ROCmFP4-GGUF
# Run inference directly in the terminal:
llama-cli -hf PatrickScully/Qwen3.6-27B-MTP-pi-reasoning-ROCmFP4-GGUF

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf PatrickScully/Qwen3.6-27B-MTP-pi-reasoning-ROCmFP4-GGUF
# Run inference directly in the terminal:
./llama-cli -hf PatrickScully/Qwen3.6-27B-MTP-pi-reasoning-ROCmFP4-GGUF

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf PatrickScully/Qwen3.6-27B-MTP-pi-reasoning-ROCmFP4-GGUF
# Run inference directly in the terminal:
./build/bin/llama-cli -hf PatrickScully/Qwen3.6-27B-MTP-pi-reasoning-ROCmFP4-GGUF

Use Docker

docker model run hf.co/PatrickScully/Qwen3.6-27B-MTP-pi-reasoning-ROCmFP4-GGUF

LM Studio
Jan

vLLM

How to use PatrickScully/Qwen3.6-27B-MTP-pi-reasoning-ROCmFP4-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "PatrickScully/Qwen3.6-27B-MTP-pi-reasoning-ROCmFP4-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "PatrickScully/Qwen3.6-27B-MTP-pi-reasoning-ROCmFP4-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/PatrickScully/Qwen3.6-27B-MTP-pi-reasoning-ROCmFP4-GGUF

Ollama
How to use PatrickScully/Qwen3.6-27B-MTP-pi-reasoning-ROCmFP4-GGUF with Ollama:
```
ollama run hf.co/PatrickScully/Qwen3.6-27B-MTP-pi-reasoning-ROCmFP4-GGUF
```

Unsloth Studio

How to use PatrickScully/Qwen3.6-27B-MTP-pi-reasoning-ROCmFP4-GGUF with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for PatrickScully/Qwen3.6-27B-MTP-pi-reasoning-ROCmFP4-GGUF to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for PatrickScully/Qwen3.6-27B-MTP-pi-reasoning-ROCmFP4-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for PatrickScully/Qwen3.6-27B-MTP-pi-reasoning-ROCmFP4-GGUF to start chatting

How to use PatrickScully/Qwen3.6-27B-MTP-pi-reasoning-ROCmFP4-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf PatrickScully/Qwen3.6-27B-MTP-pi-reasoning-ROCmFP4-GGUF

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "PatrickScully/Qwen3.6-27B-MTP-pi-reasoning-ROCmFP4-GGUF"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use PatrickScully/Qwen3.6-27B-MTP-pi-reasoning-ROCmFP4-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf PatrickScully/Qwen3.6-27B-MTP-pi-reasoning-ROCmFP4-GGUF

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default PatrickScully/Qwen3.6-27B-MTP-pi-reasoning-ROCmFP4-GGUF

Run Hermes

hermes

Atomic Chat new
Docker Model Runner
How to use PatrickScully/Qwen3.6-27B-MTP-pi-reasoning-ROCmFP4-GGUF with Docker Model Runner:
```
docker model run hf.co/PatrickScully/Qwen3.6-27B-MTP-pi-reasoning-ROCmFP4-GGUF
```

Lemonade

How to use PatrickScully/Qwen3.6-27B-MTP-pi-reasoning-ROCmFP4-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull PatrickScully/Qwen3.6-27B-MTP-pi-reasoning-ROCmFP4-GGUF

Run and chat with the model

lemonade run user.Qwen3.6-27B-MTP-pi-reasoning-ROCmFP4-GGUF-{{QUANT_TAG}}

List all available models

lemonade list

Qwen3.6-27B-MTP-pi-reasoning · ROCmFP4 (STRIX)

A ROCmFP4 4-bit quant of bytkim/Qwen3.6-27B-MTP-pi-reasoning-GGUF, built for AMD Strix Halo (Ryzen AI MAX+, gfx1151) with multi-token-prediction (MTP) self-speculative decoding. Quantized from the BF16 source with the Q4_0_ROCMFP4_STRIX quality preset.

⚠️ This is not a stock GGUF. The q4_0_rocmfp4 / q4_0_rocmfp4_fast tensor types only load in the charlie12345/rocmfp4-llama fork of llama.cpp (branch mtp-rocmfp4-strix). It will not load in upstream llama.cpp, LM Studio, Ollama, Jan, or koboldcpp. Hugging Face's auto-parser may mislabel the file as "F16"; it is really a ~4.4 bpw 4-bit model.

What is ROCmFP4?

ROCmFP4 is an AMD-focused 4-bit GGUF weight format from the fork above. It pairs a Codebook10 4-bit value table with finite unsigned E4M3 half-scales, in two layouts:

q4_0_rocmfp4: dual-scale (~4.5 bpw), used on precision-sensitive tensors (attention projections here).
q4_0_rocmfp4_fast: single-scale (~4.25 bpw), used on the bulk of the network for speed.

The _STRIX preset is a tensor-aware mix. It protects what matters for coherence while keeping the body small and fast on the AMD ROCm/HIP and Vulkan paths.

This build


Format	ROCmFP4 4-bit (`Q4_0_ROCMFP4_STRIX`)
Effective precision	4.38 bpw
File size	~14.0 GiB (14,986,109,152 bytes)
Architecture	`qwen35` hybrid attention + SSM, 65 blocks (64 plus 1 MTP)
Context	up to 262,144 tokens
MTP	`nextn` draft head carried through (self-speculative)
imatrix	none (plain preset quant)
Vision	not included, language weights only (see note below)

Tensor recipe (as quantized):

Tensor group	Type
`token_embd`	`q6_K`
attention K/V projections	`q4_0_rocmfp4` (dual-scale)
FFN, `output` (lm-head), MTP `eh_proj`, rest	`q4_0_rocmfp4_fast` (single-scale)
norms, SSM params (`ssm_*`), MTP norms	`f32`

Quick start (llama.cpp fork)

Build the fork first (see its README; Strix uses scripts/build-strix-rocmfp4-mtp.sh), then:

HSA_OVERRIDE_GFX_VERSION=11.5.1 \
GGML_HIP_ENABLE_UNIFIED_MEMORY=1 \
./build-strix-rocmfp4/bin/llama-server \
  -m Qwen3.6-27B-MTP-pi-reasoning-ROCmFP4-STRIX.gguf \
  -dev ROCm0 -ngl 999 \
  -c 262144 -b 512 -ub 512 -fa on \
  -ctk q4_0 -ctv q4_0 \
  --spec-type draft-mtp \
  --spec-draft-type-k q4_0 --spec-draft-type-v q4_0 \
  --spec-draft-n-max 4 --spec-draft-n-min 0 \
  --spec-draft-p-min 0.0 --spec-draft-p-split 0.10 \
  --reasoning on --jinja

Drop the --spec-* flags to run without MTP, or the --reasoning/--jinja flags for plain completion.

Local performance

Measured on a Framework Desktop / Ryzen AI MAX+ 395, Radeon 8060S (gfx1151), 128 GB unified memory, ROCm backend, fork build 4795079b0. Numbers are local and depend on driver, context, and prompt.

Raw throughput, llama-bench (-ngl 999 -fa 1 -r 3), no speculative decoding:

test	t/s
prefill (pp512)	389.3 ± 2.4
decode (tg128)	13.8 ± 0.03

llama-bench cannot exercise MTP, so the decode figure above is raw single-token decode. MTP self-speculative decoding (the intended way to run this model) roughly doubles it, with the gain depending heavily on how predictable the output is. Measured on llama-server over 256-token generations:

Workload	Decode tok/s	Draft acceptance
Code generation	~35.5	~74% (190/257)
Short reasoning	~34.9	~72% (88/123)
Free-form reasoning	~27.1	~51% (170/335)

So expect roughly 27 to 36 tok/s with MTP (about 2x to 2.6x over raw decode), trending higher on code and structured output.

Reproduce

# source: the BF16 GGUF from bytkim
./build-strix-rocmfp4/bin/llama-quantize \
  Qwen3.6-27B-MTP-pi-reasoning-bf16.gguf \
  Qwen3.6-27B-MTP-pi-reasoning-ROCmFP4-STRIX.gguf \
  Q4_0_ROCMFP4_STRIX

Vision

The source model is vision-capable via the Qwen3.6 mmproj-F16.gguf sidecar, but this repo ships language weights only. To enable images, pair this GGUF with the matching mmproj from the source repo and pass --mmproj to the fork.

Lineage & credits

Base model: Qwen/Qwen3.6-27B (Qwen team)
Fine-tune / BF16 source: bytkim/Qwen3.6-27B-MTP-pi-reasoning-GGUF, a QLoRA SFT on agent trajectories with MTP and "pi-reasoning"
Format & runtime: charlie12345/rocmfp4-llama (llama.cpp fork, MIT)

License

Apache 2.0, inherited from the upstream Qwen3.6-27B base model. You may use, modify, and redistribute this quant and its derivatives subject to that license.

Downloads last month: -

GGUF

Model size

27B params

Architecture

qwen35

Hardware compatibility

We're not able to determine the quantization variants.

View all variants

Model tree for PatrickScully/Qwen3.6-27B-MTP-pi-reasoning-ROCmFP4-GGUF

Base model

Qwen/Qwen3.6-27B

Finetuned

bytkim/Qwen3.6-27B-MTP-pi-reasoning-GGUF

Quantized

(1)

this model