Instructions to use raulvidis/Qwen3.6-35B-A3B-ROCmFP4_FAST-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 raulvidis/Qwen3.6-35B-A3B-ROCmFP4_FAST-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 raulvidis/Qwen3.6-35B-A3B-ROCmFP4_FAST-GGUF:Q4_0
# Run inference directly in the terminal:
llama cli -hf raulvidis/Qwen3.6-35B-A3B-ROCmFP4_FAST-GGUF:Q4_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf raulvidis/Qwen3.6-35B-A3B-ROCmFP4_FAST-GGUF:Q4_0
# Run inference directly in the terminal:
llama cli -hf raulvidis/Qwen3.6-35B-A3B-ROCmFP4_FAST-GGUF:Q4_0

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 raulvidis/Qwen3.6-35B-A3B-ROCmFP4_FAST-GGUF:Q4_0
# Run inference directly in the terminal:
./llama-cli -hf raulvidis/Qwen3.6-35B-A3B-ROCmFP4_FAST-GGUF:Q4_0

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 raulvidis/Qwen3.6-35B-A3B-ROCmFP4_FAST-GGUF:Q4_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf raulvidis/Qwen3.6-35B-A3B-ROCmFP4_FAST-GGUF:Q4_0

Use Docker

docker model run hf.co/raulvidis/Qwen3.6-35B-A3B-ROCmFP4_FAST-GGUF:Q4_0

LM Studio
Jan

vLLM

How to use raulvidis/Qwen3.6-35B-A3B-ROCmFP4_FAST-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "raulvidis/Qwen3.6-35B-A3B-ROCmFP4_FAST-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": "raulvidis/Qwen3.6-35B-A3B-ROCmFP4_FAST-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/raulvidis/Qwen3.6-35B-A3B-ROCmFP4_FAST-GGUF:Q4_0

Ollama
How to use raulvidis/Qwen3.6-35B-A3B-ROCmFP4_FAST-GGUF with Ollama:
```
ollama run hf.co/raulvidis/Qwen3.6-35B-A3B-ROCmFP4_FAST-GGUF:Q4_0
```

Unsloth Studio

How to use raulvidis/Qwen3.6-35B-A3B-ROCmFP4_FAST-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 raulvidis/Qwen3.6-35B-A3B-ROCmFP4_FAST-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 raulvidis/Qwen3.6-35B-A3B-ROCmFP4_FAST-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for raulvidis/Qwen3.6-35B-A3B-ROCmFP4_FAST-GGUF to start chatting

How to use raulvidis/Qwen3.6-35B-A3B-ROCmFP4_FAST-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf raulvidis/Qwen3.6-35B-A3B-ROCmFP4_FAST-GGUF:Q4_0

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": "raulvidis/Qwen3.6-35B-A3B-ROCmFP4_FAST-GGUF:Q4_0"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use raulvidis/Qwen3.6-35B-A3B-ROCmFP4_FAST-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 raulvidis/Qwen3.6-35B-A3B-ROCmFP4_FAST-GGUF:Q4_0

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 raulvidis/Qwen3.6-35B-A3B-ROCmFP4_FAST-GGUF:Q4_0

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use raulvidis/Qwen3.6-35B-A3B-ROCmFP4_FAST-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf raulvidis/Qwen3.6-35B-A3B-ROCmFP4_FAST-GGUF:Q4_0

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 "raulvidis/Qwen3.6-35B-A3B-ROCmFP4_FAST-GGUF:Q4_0" \
  --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"

Docker Model Runner
How to use raulvidis/Qwen3.6-35B-A3B-ROCmFP4_FAST-GGUF with Docker Model Runner:
```
docker model run hf.co/raulvidis/Qwen3.6-35B-A3B-ROCmFP4_FAST-GGUF:Q4_0
```

Lemonade

How to use raulvidis/Qwen3.6-35B-A3B-ROCmFP4_FAST-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull raulvidis/Qwen3.6-35B-A3B-ROCmFP4_FAST-GGUF:Q4_0

Run and chat with the model

lemonade run user.Qwen3.6-35B-A3B-ROCmFP4_FAST-GGUF-Q4_0

List all available models

lemonade list

Qwen3.6-35B-A3B — Q4_0-ROCmFP4_FAST (GGUF)

A ROCmFP4_FAST (4.25 bpw) quantization of Qwen3.6-35B-A3B, tuned for the AMD Strix Halo iGPU (Radeon 8060S, gfx1151, RDNA3.5). Quantized directly from the BF16 source with the MTP (nextn) head preserved.

⚠️ Requires the ROCmFPX fork — will NOT load in stock llama.cpp

ROCmFP4 is a custom weight format built on a Q4_0 base. This file only runs on the ROCmFPX fork of llama.cpp: https://github.com/charlie12345/ROCmFPX. Loading it in upstream llama.cpp, Ollama, LM Studio, etc. will fail. Build the fork (scripts/build-strix-rocmfp4-mtp.sh) and use its llama-server.

Why ROCmFP4_FAST

Measured on a Framework Desktop (Ryzen AI Max+ 395, Radeon 8060S gfx1151, ROCm 7.2, Vulkan backend), against Q4_K_M of the same base weights, plain decode:

format	decode (short)	decode (~40k ctx)	prefill	file size
Q4_K_M	67.6 t/s	55.9 t/s	211 / 746 t/s	21 GB
ROCmFP4_FAST	73.0 t/s	59.5 t/s	232 / 784 t/s	18 GB
delta	+8%	+6.4%	+5–10%	−14%

Single-user, -fa on, f16 KV, Vulkan. Your mileage varies by driver/build.

Quality holds vs higher precision: in blind-graded coding benchmarks this FP4_FAST quant scored within noise of the BF16 source (same band), so the format costs little to no accuracy — the big quality lever is the reasoning mode below, not the quant.

Files

filename	quant	notes
`Qwen3.6-35B-A3B-Q4_0-ROCmFP4_FAST.gguf`	Q4_0_ROCMFP4_FAST (4.25 bpw)	MTP/nextn head included

Run

# built ROCmFPX fork
llama-server \
  --model Qwen3.6-35B-A3B-Q4_0-ROCmFP4_FAST.gguf \
  -dev Vulkan0 -ngl 999 -fa on -c 131072 \
  -ctk f16 -ctv f16 --jinja --host 0.0.0.0 --port 8080

The GGUF carries an MTP (nextn) head, so speculative decoding works with --spec-type draft-mtp. On this hardware, conservative draft settings work best (e.g. --spec-draft-n-max 4 --spec-draft-p-min 0.55); high n_max tends to regress decode.

Sampling & reasoning (thinking on/off)

Recommended sampling (validated on this stack): --temp 0.7 --top-p 0.8 --top-k 20 --min-p 0 --presence-penalty 0.

Reasoning is task-dependent — it is the single most important serving choice for this model. Blind-graded coding benchmarks on this quant (0–100, same-grader; unknown-cause debugging suite + fully-specified implementation suite):

task type	thinking OFF	thinking ON
fully-specified implementation ("build X, constraints 1–N, output full file")	~88	~81
unknown-cause debugging / hard algorithms / judgment	~38	~66

Default: thinking OFF — --reasoning off --reasoning-format deepseek --reasoning-budget 0. Best for agentic / well-specified coding: ~8× lower latency, cleaner output, and it scores higher than thinking-on on well-specified work. The right mode for delegated "implement X with these constraints" tasks.
Debugging / hard reasoning: thinking ON — --reasoning-format deepseek --reasoning-budget 4096. For "find why this misbehaves", novel algorithms, review/critique, or planning, reasoning is worth roughly +28 points and the extra latency. Without it the model tends to loop and leak deliberation into the answer.

Keep --reasoning-format deepseek in both modes — it ensures <think> blocks are parsed and closed correctly (Qwen3.6 can otherwise leak an unclosed <think> into the output).

Provenance & credits

Base weights: unsloth/Qwen3.6-35B-A3B-MTP-GGUF (BF16 source).
Quant format & tooling: ROCmFPX (llama-quantize ... Q4_0_ROCMFP4_FAST).
License inherited from the base model.

Quantized 2026-07 for a Strix Halo inference stack.

Downloads last month: 617

GGUF

Model size

36B params

Architecture

qwen35moe

Hardware compatibility

4-bit

Model tree for raulvidis/Qwen3.6-35B-A3B-ROCmFP4_FAST-GGUF

Base model

Qwen/Qwen3.6-35B-A3B

Quantized

unsloth/Qwen3.6-35B-A3B-MTP-GGUF

Quantized

(7)

this model