Instructions to use philtheriver/Qwopus3.6-27B-v2-MTP-ROCmFPX with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use philtheriver/Qwopus3.6-27B-v2-MTP-ROCmFPX with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="philtheriver/Qwopus3.6-27B-v2-MTP-ROCmFPX",
	filename="Qwopus3.6-27B-v2-MTP-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/Qwopus3.6-27B-v2-MTP-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/Qwopus3.6-27B-v2-MTP-ROCmFPX:BF16
# Run inference directly in the terminal:
llama cli -hf philtheriver/Qwopus3.6-27B-v2-MTP-ROCmFPX:BF16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf philtheriver/Qwopus3.6-27B-v2-MTP-ROCmFPX:BF16
# Run inference directly in the terminal:
llama cli -hf philtheriver/Qwopus3.6-27B-v2-MTP-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/Qwopus3.6-27B-v2-MTP-ROCmFPX:BF16
# Run inference directly in the terminal:
./llama-cli -hf philtheriver/Qwopus3.6-27B-v2-MTP-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/Qwopus3.6-27B-v2-MTP-ROCmFPX:BF16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf philtheriver/Qwopus3.6-27B-v2-MTP-ROCmFPX:BF16

Use Docker

docker model run hf.co/philtheriver/Qwopus3.6-27B-v2-MTP-ROCmFPX:BF16

LM Studio
Jan

vLLM

How to use philtheriver/Qwopus3.6-27B-v2-MTP-ROCmFPX with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "philtheriver/Qwopus3.6-27B-v2-MTP-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/Qwopus3.6-27B-v2-MTP-ROCmFPX",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/philtheriver/Qwopus3.6-27B-v2-MTP-ROCmFPX:BF16

Ollama
How to use philtheriver/Qwopus3.6-27B-v2-MTP-ROCmFPX with Ollama:
```
ollama run hf.co/philtheriver/Qwopus3.6-27B-v2-MTP-ROCmFPX:BF16
```

Unsloth Studio

How to use philtheriver/Qwopus3.6-27B-v2-MTP-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/Qwopus3.6-27B-v2-MTP-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/Qwopus3.6-27B-v2-MTP-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/Qwopus3.6-27B-v2-MTP-ROCmFPX to start chatting

How to use philtheriver/Qwopus3.6-27B-v2-MTP-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/Qwopus3.6-27B-v2-MTP-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/Qwopus3.6-27B-v2-MTP-ROCmFPX:BF16"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use philtheriver/Qwopus3.6-27B-v2-MTP-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/Qwopus3.6-27B-v2-MTP-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/Qwopus3.6-27B-v2-MTP-ROCmFPX:BF16

Run Hermes

hermes

Atomic Chat new
Docker Model Runner
How to use philtheriver/Qwopus3.6-27B-v2-MTP-ROCmFPX with Docker Model Runner:
```
docker model run hf.co/philtheriver/Qwopus3.6-27B-v2-MTP-ROCmFPX:BF16
```

Lemonade

How to use philtheriver/Qwopus3.6-27B-v2-MTP-ROCmFPX with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull philtheriver/Qwopus3.6-27B-v2-MTP-ROCmFPX:BF16

Run and chat with the model

lemonade run user.Qwopus3.6-27B-v2-MTP-ROCmFPX-BF16

List all available models

lemonade list

Qwopus3.6-27B-v2 · ROCmFPX

Stock `Q6_K` quality, ~25% faster prompt-processing on AMD Strix Halo (`gfx1151`)

ROCmFPX 3→8-bit quants of Jackrong/Qwopus3.6-27B-v2-MTP-GGUF — the general-purpose 27B Qwopus, MTP speculative decoding + Qwen3-VL vision, agent/tool-use tuned.


Quality	≈ stock `Q6_K` — PPL +0.28% (within error)
Prompt processing	+27% vs Q6_K (short ctx) → +16% at 64k
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_AGENT.gguf` ★	26 GB	best overall — the flagship
`…embF16-Q8_0_ROCMFPX.gguf`	29 GB	maximum fidelity
`…embF16-Q4_0_ROCMFP4.gguf`	19 GB	fastest decode (4-bit)
`…embF16-Q3_0_ROCMFPX.gguf`	17 GB	smallest

Agent-routed _AGENT tiers + the full enum/bpw table are in the details below and the Files tab. All filenames prefixed Qwopus3.6-27B-v2-MTP-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 Qwopus3.6-27B-v2-MTP-STRIX-embF16-headQ6-Q6_0_ROCMFPX_AGENT.gguf \
  -dev ROCm0 -ngl 999 -fa on -c 131072 \
  --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: point your client at the qwen3_coder parser, or the model narrates instead of emitting structured calls.

All tiers · recipe · benchmarks

All tiers

File suffix	Preset	Enum	Size	Role
`embF16-headQ6-Q6_0_ROCMFPX_AGENT.gguf`	`Q6_0_ROCMFPX_AGENT`	114	26 GB	flagship — f16 emb + Q6_K head + imatrix
`embF16-Q8_0_ROCMFPX_AGENT.gguf`	`Q8_0_ROCMFPX_AGENT`	115	30 GB	highest-fidelity agent
`embF16-Q8_0_ROCMFPX.gguf`	`Q8_0_ROCMFPX`	111	29 GB	highest fidelity
`embF16-Q6_0_ROCMFPX.gguf`	`Q6_0_ROCMFPX`	110	24 GB	balanced
`embF16-Q3_0_ROCMFPX_AGENT.gguf`	`Q3_0_ROCMFPX_AGENT`	113	21 GB	smallest agent
`embF16-Q3_0_ROCMFPX.gguf`	`Q3_0_ROCMFPX`	112	17 GB	smallest
`embF16-Q4_0_ROCMFP4.gguf`	`Q4_0_ROCMFP4`	100	19 GB	fastest decode (4-bit body)

f16 token embeddings throughout; _AGENT presets keep attention/FFN routing at higher precision for tool-call/JSON coherence. (HF labels Q4/Q8 but not Q6/Q3 — the latter aren't standard llama.cpp quant names.)

Verification (Strix Halo gfx1151)

Metric	Value
Functional smoke	chat/coding/JSON/tool-call/coherency ✅ (5/5)
PPL vs `Q6_K` (code corpus)	flagship 2.962 vs Q6_K 2.954 → +0.28% (within ±0.04)

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

Context	`Q6_K`	flagship	Δ
pp512	195	248	+27%
pp2048	189	242	+28%
pp10k	179	222	+24%
pp16k	172	208	+21%
pp32k	157	186	+19%
pp64k	133	155	+16%

The gfx1151-tuned kernels win the compute-bound prefill; the edge is largest at short context and narrows toward +16% 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. Q4_0_ROCMFP4 is the decode king (~13 tok/s raw). Single-rep llama-bench, ran warm — absolutes run a touch conservative vs the Coder sibling.

Credits & license

Apache-2.0 (inherited). Jackrong + Kyle Hessling (fine-tune) → Qwen3.6-27B (base) → charlie12345 / ROCmFPX (quant fork). ROCmFPX quantization by this repo's author.

Downloads last month: 315

GGUF

Model size

27B params

Architecture

qwen35

Hardware compatibility

4-bit

8-bit

16-bit

Model tree for philtheriver/Qwopus3.6-27B-v2-MTP-ROCmFPX

Base model

Qwen/Qwen3.6-27B

Adapter

Jackrong/Qwopus3.6-27B-v2-MTP-GGUF

Quantized

(3)

this model