Instructions to use philtheriver/Qwen3.6-27B-ROCmFPX with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use philtheriver/Qwen3.6-27B-ROCmFPX with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="philtheriver/Qwen3.6-27B-ROCmFPX",
	filename="Qwen3.6-27B-STRIX-embF16-Q3_0_ROCMFPX.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 philtheriver/Qwen3.6-27B-ROCmFPX with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf philtheriver/Qwen3.6-27B-ROCmFPX:BF16
# Run inference directly in the terminal:
llama cli -hf philtheriver/Qwen3.6-27B-ROCmFPX:BF16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf philtheriver/Qwen3.6-27B-ROCmFPX:BF16
# Run inference directly in the terminal:
llama cli -hf philtheriver/Qwen3.6-27B-ROCmFPX:BF16

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 philtheriver/Qwen3.6-27B-ROCmFPX:BF16
# Run inference directly in the terminal:
./llama-cli -hf philtheriver/Qwen3.6-27B-ROCmFPX:BF16

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 philtheriver/Qwen3.6-27B-ROCmFPX:BF16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf philtheriver/Qwen3.6-27B-ROCmFPX:BF16

Use Docker

docker model run hf.co/philtheriver/Qwen3.6-27B-ROCmFPX:BF16

LM Studio
Jan

vLLM

How to use philtheriver/Qwen3.6-27B-ROCmFPX with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/philtheriver/Qwen3.6-27B-ROCmFPX:BF16

Ollama
How to use philtheriver/Qwen3.6-27B-ROCmFPX with Ollama:
```
ollama run hf.co/philtheriver/Qwen3.6-27B-ROCmFPX:BF16
```

Unsloth Studio

How to use philtheriver/Qwen3.6-27B-ROCmFPX 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 philtheriver/Qwen3.6-27B-ROCmFPX 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 philtheriver/Qwen3.6-27B-ROCmFPX to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for philtheriver/Qwen3.6-27B-ROCmFPX to start chatting

How to use philtheriver/Qwen3.6-27B-ROCmFPX with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf philtheriver/Qwen3.6-27B-ROCmFPX:BF16

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": "philtheriver/Qwen3.6-27B-ROCmFPX:BF16"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use philtheriver/Qwen3.6-27B-ROCmFPX with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf philtheriver/Qwen3.6-27B-ROCmFPX:BF16

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 philtheriver/Qwen3.6-27B-ROCmFPX:BF16

Run Hermes

hermes

Atomic Chat new
Docker Model Runner
How to use philtheriver/Qwen3.6-27B-ROCmFPX with Docker Model Runner:
```
docker model run hf.co/philtheriver/Qwen3.6-27B-ROCmFPX:BF16
```

Lemonade

How to use philtheriver/Qwen3.6-27B-ROCmFPX with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull philtheriver/Qwen3.6-27B-ROCmFPX:BF16

Run and chat with the model

lemonade run user.Qwen3.6-27B-ROCmFPX-BF16

List all available models

lemonade list

Qwen3.6-27B · ROCmFPX

Stock `Q6_K` quality, ~30% faster prompt-processing on AMD Strix Halo (`gfx1151`)

ROCmFPX 3→8-bit quants of unsloth/Qwen3.6-27B-MTP-GGUF — the general-purpose base, with MTP speculative decoding + Qwen3-VL vision. Neutral imatrix calibration, so base behavior is preserved (not skewed toward code).


Quality	≈ stock `Q6_K` (PPL within error)
Prompt processing	+29% vs Q6_K (short ctx) → +20% at 64k — measured
Decode	~18 tok/s with MTP (~9 raw)
Vision	Qwen3-VL — bundled `mmproj/`

⚠️ Requires the ROCmFPX fork (build main — the FP* types are merged in) — custom AMD quant types (enum IDs 110–115), not upstream-stable. Won't load in stock llama.cpp / LM Studio / Ollama. HF's precision badge is wrong — pick the file by name.

Pick a tier

File suffix	Size	Best for
`…embF16-headQ6-Q6_0_ROCMFPX.gguf` ★	23G	best overall — the flagship
`…embF16-Q8_0_ROCMFPX.gguf`	28G	maximum fidelity
`…embF16-Q4_0_ROCMFP4.gguf`	19G	fastest decode (4-bit)
`…embF16-Q3_0_ROCMFPX.gguf`	16G	smallest

All filenames prefixed Qwen3.6-27B-STRIX-.

Quick start

# build the fork once — main already has the ROCmFPX quant types
git clone https://github.com/charlie12345/ROCmFPX.git && cd ROCmFPX
JOBS=16 scripts/build-strix-rocmfp4-mtp.sh

# serve the flagship — MTP + vision
HSA_OVERRIDE_GFX_VERSION=11.5.1 build-strix-rocmfp4/bin/llama-server \
  -m Qwen3.6-27B-STRIX-embF16-headQ6-Q6_0_ROCMFPX.gguf \
  -dev ROCm0 -ngl 999 -fa on -c 32768 \
  --spec-type draft-mtp --spec-draft-ngl all --spec-draft-n-max 2 \
  --jinja --mmproj mmproj/mmproj-F32.gguf --host 0.0.0.0 --port 8080

Tool calls: serve with --jinja so the model's own chat template emits them — no special parser flag needed.

All tiers · recipe · benchmarks

All tiers

File suffix	Preset	Enum	Size	Role
`embF16-headQ6-Q6_0_ROCMFPX.gguf`	`Q6_0_ROCMFPX`	110	23G	flagship — f16 emb + Q6_K head + imatrix
`embF16-Q8_0_ROCMFPX.gguf`	`Q8_0_ROCMFPX`	111	28G	highest fidelity
`embF16-Q4_0_ROCMFP4.gguf`	`Q4_0_ROCMFP4`	100	19G	fastest decode (4-bit body)
`embF16-Q3_0_ROCMFPX.gguf`	`Q3_0_ROCMFPX`	112	16G	smallest

f16 token embeddings throughout. (HF labels Q4/Q8 but not Q6/Q3 — the latter aren't standard llama.cpp quant names; pick by filename.)

Verification (Strix Halo gfx1151)

Metric	Value
Functional smoke	chat/coding/JSON/tool-call/coherency ✅ (5/5)
PPL vs `Q6_K`	flagship 5.7030 vs stock `Q6_K` 5.6618 → Δ +0.73% (general slice, ctx 512)

Performance — prompt-processing throughput (t/s) vs `Q6_K`

Context	`Q6_K`	flagship	Δ
pp512	188	242	+29%
pp2048	191	245	+28%
pp10k	180	228	+27%
pp16k	172	217	+26%
pp32k	156	193	+23%
pp64k	133	159	+20%

Clean dedicated-GPU llama-bench (both servers stopped, warm-up pass discarded). The gfx1151-tuned ROCmFPX kernels win the compute-bound prefill — the edge is largest at short context and narrows to +20% at 64k as O(n²) attention takes over. Decode is bandwidth-bound (≈ Q6_K raw), and MTP (--spec-type draft-mtp) ~doubles it in serving. Single-rep llama-bench; treat absolutes as ±a few %.

Credits & license

Apache-2.0 (inherited). Qwen3.6 (base) → charlie12345 / ROCmFPX (quant fork). ROCmFPX quantization by this repo's author.

Downloads last month: 144

GGUF

Model size

27B params

Architecture

qwen35

Hardware compatibility

4-bit

8-bit

16-bit

Model tree for philtheriver/Qwen3.6-27B-ROCmFPX

Base model

Qwen/Qwen3.6-27B

Quantized

unsloth/Qwen3.6-27B-MTP-GGUF