Instructions to use Kymidnight/Qwen3.5-122B-A10B-ROCMFP4-MTP-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 Kymidnight/Qwen3.5-122B-A10B-ROCMFP4-MTP-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 Kymidnight/Qwen3.5-122B-A10B-ROCMFP4-MTP-GGUF
# Run inference directly in the terminal:
llama cli -hf Kymidnight/Qwen3.5-122B-A10B-ROCMFP4-MTP-GGUF

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Kymidnight/Qwen3.5-122B-A10B-ROCMFP4-MTP-GGUF
# Run inference directly in the terminal:
llama cli -hf Kymidnight/Qwen3.5-122B-A10B-ROCMFP4-MTP-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 Kymidnight/Qwen3.5-122B-A10B-ROCMFP4-MTP-GGUF
# Run inference directly in the terminal:
./llama-cli -hf Kymidnight/Qwen3.5-122B-A10B-ROCMFP4-MTP-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 Kymidnight/Qwen3.5-122B-A10B-ROCMFP4-MTP-GGUF
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Kymidnight/Qwen3.5-122B-A10B-ROCMFP4-MTP-GGUF

Use Docker

docker model run hf.co/Kymidnight/Qwen3.5-122B-A10B-ROCMFP4-MTP-GGUF

LM Studio
Jan
Ollama
How to use Kymidnight/Qwen3.5-122B-A10B-ROCMFP4-MTP-GGUF with Ollama:
```
ollama run hf.co/Kymidnight/Qwen3.5-122B-A10B-ROCMFP4-MTP-GGUF
```
Unsloth Desktop

How to use Kymidnight/Qwen3.5-122B-A10B-ROCMFP4-MTP-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Kymidnight/Qwen3.5-122B-A10B-ROCMFP4-MTP-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": "Kymidnight/Qwen3.5-122B-A10B-ROCMFP4-MTP-GGUF"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use Kymidnight/Qwen3.5-122B-A10B-ROCMFP4-MTP-GGUF with Docker Model Runner:
```
docker model run hf.co/Kymidnight/Qwen3.5-122B-A10B-ROCMFP4-MTP-GGUF
```

Lemonade

How to use Kymidnight/Qwen3.5-122B-A10B-ROCMFP4-MTP-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Kymidnight/Qwen3.5-122B-A10B-ROCMFP4-MTP-GGUF

Run and chat with the model

lemonade run user.Qwen3.5-122B-A10B-ROCMFP4-MTP-GGUF-{{QUANT_TAG}}

List all available models

lemonade list

Hermes Agent

How to use Kymidnight/Qwen3.5-122B-A10B-ROCMFP4-MTP-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 Kymidnight/Qwen3.5-122B-A10B-ROCMFP4-MTP-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 Kymidnight/Qwen3.5-122B-A10B-ROCMFP4-MTP-GGUF

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use Kymidnight/Qwen3.5-122B-A10B-ROCMFP4-MTP-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Kymidnight/Qwen3.5-122B-A10B-ROCMFP4-MTP-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 "Kymidnight/Qwen3.5-122B-A10B-ROCMFP4-MTP-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"

Qwen3.5-122B-A10B-ROCMFP4-MTP-GGUF

The first ROCmFP4 MTP quantization of Qwen3.5-122B optimized for AMD Strix Halo (Ryzen AI 300 series) APUs.

Key Features

Format: GGUF with integrated MTP (Multi-Token Prediction) head
Quantization: ROCmFP4 (custom 4-bit quantization for AMD GPUs)
Architecture: A10B (Adaptive 10/40 layer hybrid attention for 128K context)
Context: 256K tokens
MTP Acceptance: 92-95%

Benchmarks (Strix Halo 128GB, Aug 25 2026)

Tested with llama.cpp ROCmFPX b257, Vulkan backend, MTP enabled.

Prompt Size	Prompt Speed	Gen Speed
36 tokens	91.5 t/s	43.8 t/s
71 tokens	99.2 t/s	39.3 t/s
932 tokens	379.6 t/s	41.0 t/s

Generation: ~41-44 t/s (consistent across prompt sizes)
Prompt processing: up to 380 t/s (large prompts saturate GPU bandwidth)
MTP accept rate: 94%
Model size: ~65 GB (5 shards)

Usage

llama-server \  --model Qwen3.5-122B-A10B-ROCMFP4-STRIX-00001-of-00002-00001-of-00005.gguf \  --port 8080 \  -c 262144 \  --n-gpu-layers 99 \  --spec-type draft-mtp \  --spec-draft-n-max 2 \  --spec-draft-n-min 1 \  --spec-draft-p-min 0.75 \  --spec-draft-type-k q8_0 \  --spec-draft-type-v q8_0

Notes

Built with llama.cpp b10615+ (ROCmFPX b257)
Requires AMD ROCm 6.2+ or Vulkan backend
MTP head is bundled in the GGUF (no separate draft model needed)
Optimized for 128GB+ VRAM systems
Hybrid attention (10/40 full layers) enables 256K context in 128GB VRAM

License

Apache 2.0

Generated by Tom Yoder | August 2026

Downloads last month: 1,434

GGUF

Model size

125B params

Architecture

qwen35moe

Hardware compatibility

We're not able to determine the quantization variants.

View all variants

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support