Instructions to use lmcoleman/Qwen3.6-35B-A3B-ROCmFPX-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use lmcoleman/Qwen3.6-35B-A3B-ROCmFPX-GGUF 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 lmcoleman/Qwen3.6-35B-A3B-ROCmFPX-GGUF
# Run inference directly in the terminal:
llama cli -hf lmcoleman/Qwen3.6-35B-A3B-ROCmFPX-GGUF

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf lmcoleman/Qwen3.6-35B-A3B-ROCmFPX-GGUF
# Run inference directly in the terminal:
llama cli -hf lmcoleman/Qwen3.6-35B-A3B-ROCmFPX-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 lmcoleman/Qwen3.6-35B-A3B-ROCmFPX-GGUF
# Run inference directly in the terminal:
./llama-cli -hf lmcoleman/Qwen3.6-35B-A3B-ROCmFPX-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 lmcoleman/Qwen3.6-35B-A3B-ROCmFPX-GGUF
# Run inference directly in the terminal:
./build/bin/llama-cli -hf lmcoleman/Qwen3.6-35B-A3B-ROCmFPX-GGUF

Use Docker

docker model run hf.co/lmcoleman/Qwen3.6-35B-A3B-ROCmFPX-GGUF

LM Studio
Jan

vLLM

How to use lmcoleman/Qwen3.6-35B-A3B-ROCmFPX-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "lmcoleman/Qwen3.6-35B-A3B-ROCmFPX-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": "lmcoleman/Qwen3.6-35B-A3B-ROCmFPX-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/lmcoleman/Qwen3.6-35B-A3B-ROCmFPX-GGUF

Ollama
How to use lmcoleman/Qwen3.6-35B-A3B-ROCmFPX-GGUF with Ollama:
```
ollama run hf.co/lmcoleman/Qwen3.6-35B-A3B-ROCmFPX-GGUF
```

Unsloth Studio

How to use lmcoleman/Qwen3.6-35B-A3B-ROCmFPX-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 lmcoleman/Qwen3.6-35B-A3B-ROCmFPX-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 lmcoleman/Qwen3.6-35B-A3B-ROCmFPX-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for lmcoleman/Qwen3.6-35B-A3B-ROCmFPX-GGUF to start chatting

How to use lmcoleman/Qwen3.6-35B-A3B-ROCmFPX-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf lmcoleman/Qwen3.6-35B-A3B-ROCmFPX-GGUF

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "lmcoleman/Qwen3.6-35B-A3B-ROCmFPX-GGUF"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use lmcoleman/Qwen3.6-35B-A3B-ROCmFPX-GGUF with Docker Model Runner:
```
docker model run hf.co/lmcoleman/Qwen3.6-35B-A3B-ROCmFPX-GGUF
```

Lemonade

How to use lmcoleman/Qwen3.6-35B-A3B-ROCmFPX-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull lmcoleman/Qwen3.6-35B-A3B-ROCmFPX-GGUF

Run and chat with the model

lemonade run user.Qwen3.6-35B-A3B-ROCmFPX-GGUF-{{QUANT_TAG}}

List all available models

lemonade list

Hermes Agent

How to use lmcoleman/Qwen3.6-35B-A3B-ROCmFPX-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf lmcoleman/Qwen3.6-35B-A3B-ROCmFPX-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 lmcoleman/Qwen3.6-35B-A3B-ROCmFPX-GGUF

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use lmcoleman/Qwen3.6-35B-A3B-ROCmFPX-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf lmcoleman/Qwen3.6-35B-A3B-ROCmFPX-GGUF

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "lmcoleman/Qwen3.6-35B-A3B-ROCmFPX-GGUF" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

Qwen3.6-35B-A3B-ROCmFPX-GGUF / README.md

lmcoleman

Upload README.md with huggingface_hub

b791954 verified 25 days ago

preview code

Raw

History Blame Contribute Delete

4.6 kB

	---
	license: apache-2.0
	library_name: llama.cpp
	base_model:
	- Qwen/Qwen3.6-35B-A3B
	base_model_relation: quantized
	pipeline_tag: text-generation
	quantized_by: ROCmFPX
	language:
	- en
	tags:
	- gguf
	- rocm
	- amd
	- strix-halo
	- gfx1151
	- rocmfpx
	- quantized
	- magicquant
	---

	# Qwen3.6-35B-A3B-ROCmFPX-GGUF

	> ## ⚠️ These files do NOT load on standard llama.cpp
	> They use AMD-native `*_ROCMFPX` tensor types from the experimental
	> [ciru-ai/ROCmFPX](https://github.com/ciru-ai/ROCmFPX) llama.cpp fork (build from source).

	Derivative of [Qwen3.6-35B-A3B](https://huggingface.co/Qwen/Qwen3.6-35B-A3B), quantized using MagicQuant hybrid evolutionary per-tensor search and quantized to AMD-native [ROCmFPX](https://github.com/ciru-ai/ROCmFPX) formats (fork-only) tuned for Strix Halo (gfx1151).

	## Base Model

	This is a derivative of [Qwen3.6-35B-A3B](https://huggingface.co/Qwen/Qwen3.6-35B-A3B).
	All credit for the base model architecture and weights goes to the original authors.
	The base model's license applies to this derivative.

	## Quantization Method

	Quantized using [MagicQuant](https://github.com/lucasmcoleman/MagicQuant) hybrid evolutionary per-tensor quantization,
	based on the methodology by [magiccodingman](https://github.com/magiccodingman/MagicQuant-Wiki):

	- Tensors are classified into sensitivity groups (Embeddings, Head, Query, Key, Output, FFN Up/Down, MoE Experts, Router)
	- An evolutionary search finds the optimal quantization type per group, balancing size vs. perplexity
	- Q4/Q5/Q6 tier targets are produced with different size-quality tradeoffs
	- Small-row tensors and sensitivity-critical layers (embeddings, output head, router) are kept at F32/F16/BF16
	- This is NOT a uniform quantization -- each tensor group gets its own optimal type

	## ROCmFPX (AMD-native, fork-only)

	These GGUFs use AMD-native quantization schemes from the experimental
	[ciru-ai/ROCmFPX](https://github.com/ciru-ai/ROCmFPX) llama.cpp fork,
	tuned for and benchmarked on AMD Strix Halo (Radeon 8060S iGPU, gfx1151, unified memory):

	- `ROCmFP3/4/6/8` tensor types with straight and "agent" presets (agent presets keep
	tool-calling / JSON-structured output reliable at low bit-widths)
	- Files load only on the fork -- it is an experimental upstream research
	build, so build from the pinned commit that produced these files (the
	default branch may have moved on since):

	```bash
	git clone https://github.com/ciru-ai/ROCmFPX.git ROCmFPX
	cd ROCmFPX
	git checkout 68f23f34c12d7e61177a034b0d8d3fea2129565e
	# then build per the fork's own README
	```

	## GGUF Files

	\| File \| Size \| Quant \|
	\|------\|------\|-------\|
	\| [Qwen3.6-35B-A3B-ROCMFPX-MQ-Q4.gguf](./Qwen3.6-35B-A3B-ROCMFPX-MQ-Q4.gguf) \| 22.7 GB \| MagicQuant Q4 layout in ROCmFPX types (hybrid, fork-only) \|

	## Usage

	Requires a from-source build of the [ROCmFPX fork](https://github.com/ciru-ai/ROCmFPX)
	(stock llama.cpp, LM Studio, and Ollama cannot load these files):

	```bash
	# Interactive chat (--jinja uses the model's embedded chat template)
	llama-cli -m Qwen3.6-35B-A3B-ROCMFPX-MQ-Q4.gguf -c 8192 --jinja -cnv

	# Server mode
	llama-server -m Qwen3.6-35B-A3B-ROCMFPX-MQ-Q4.gguf -c 8192 --port 8080 -ngl 99 -fa on --jinja
	```

	## Serving: MTP Speculative Decoding

	This model includes MTP ("nextn") draft tensors, enabling self-speculative
	decoding -- measured ~1.6-1.9x faster generation with a ~95% first-token
	accept rate (no separate draft model needed; it drafts from itself):

	```bash
	llama-server -m Qwen3.6-35B-A3B-ROCMFPX-MQ-Q4.gguf -c 8192 --port 8080 --host 127.0.0.1 -ngl 99 -md Qwen3.6-35B-A3B-ROCMFPX-MQ-Q4.gguf --spec-type draft-mtp -ctk q8_0 -ctv q8_0 -fa on
	```

	Memory cost: MTP needs its own draft context alongside the main context,
	so serving with it uses roughly 2x the model's memory compared to serving
	without ``-md``/``--spec-type draft-mtp``.

	## Caveats

	- The base model's license (apache-2.0) applies to all derivative files
	- Fork-only files: stock llama.cpp, LM Studio, and Ollama cannot load these -- build [ciru-ai/ROCmFPX](https://github.com/ciru-ai/ROCmFPX) from source
	- Quantization reduces precision -- verify outputs for your specific use case
	- The hybrid quantization assigns different precision to different tensor groups, which means quality characteristics may differ from uniform quantizations

	## Limitations

	- Quantized models may exhibit subtle differences from the full-precision fine-tune
	- This model inherits any limitations and biases present in the base model

	---
	Generated with [MagicQuant](https://github.com/lucasmcoleman/MagicQuant)