Instructions to use unsloth/Qwen3.5-35B-A3B-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 unsloth/Qwen3.5-35B-A3B-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 unsloth/Qwen3.5-35B-A3B-GGUF:UD-Q4_K_XL
# Run inference directly in the terminal:
llama cli -hf unsloth/Qwen3.5-35B-A3B-GGUF:UD-Q4_K_XL

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf unsloth/Qwen3.5-35B-A3B-GGUF:UD-Q4_K_XL
# Run inference directly in the terminal:
llama cli -hf unsloth/Qwen3.5-35B-A3B-GGUF:UD-Q4_K_XL

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 unsloth/Qwen3.5-35B-A3B-GGUF:UD-Q4_K_XL
# Run inference directly in the terminal:
./llama-cli -hf unsloth/Qwen3.5-35B-A3B-GGUF:UD-Q4_K_XL

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 unsloth/Qwen3.5-35B-A3B-GGUF:UD-Q4_K_XL
# Run inference directly in the terminal:
./build/bin/llama-cli -hf unsloth/Qwen3.5-35B-A3B-GGUF:UD-Q4_K_XL

Use Docker

docker model run hf.co/unsloth/Qwen3.5-35B-A3B-GGUF:UD-Q4_K_XL

LM Studio
Jan

vLLM

How to use unsloth/Qwen3.5-35B-A3B-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "unsloth/Qwen3.5-35B-A3B-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": "unsloth/Qwen3.5-35B-A3B-GGUF",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/unsloth/Qwen3.5-35B-A3B-GGUF:UD-Q4_K_XL

Ollama
How to use unsloth/Qwen3.5-35B-A3B-GGUF with Ollama:
```
ollama run hf.co/unsloth/Qwen3.5-35B-A3B-GGUF:UD-Q4_K_XL
```
Unsloth Desktop

How to use unsloth/Qwen3.5-35B-A3B-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf unsloth/Qwen3.5-35B-A3B-GGUF:UD-Q4_K_XL

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": "unsloth/Qwen3.5-35B-A3B-GGUF:UD-Q4_K_XL"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use unsloth/Qwen3.5-35B-A3B-GGUF with Docker Model Runner:
```
docker model run hf.co/unsloth/Qwen3.5-35B-A3B-GGUF:UD-Q4_K_XL
```

Lemonade

How to use unsloth/Qwen3.5-35B-A3B-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull unsloth/Qwen3.5-35B-A3B-GGUF:UD-Q4_K_XL

Run and chat with the model

lemonade run user.Qwen3.5-35B-A3B-GGUF-UD-Q4_K_XL

List all available models

lemonade list

Hermes Agent

How to use unsloth/Qwen3.5-35B-A3B-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 unsloth/Qwen3.5-35B-A3B-GGUF:UD-Q4_K_XL

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 unsloth/Qwen3.5-35B-A3B-GGUF:UD-Q4_K_XL

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use unsloth/Qwen3.5-35B-A3B-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf unsloth/Qwen3.5-35B-A3B-GGUF:UD-Q4_K_XL

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 "unsloth/Qwen3.5-35B-A3B-GGUF:UD-Q4_K_XL" \
  --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"

New to all things HF and AI, but bugs I am familiar with. ROCm: illegal memory access. Model: Qwen3.5-35B-A3B-Q4_K_M

#40

by jwallgood - opened Mar 17

Discussion

jwallgood

Mar 17

lot launch_slot_: id 3 | task -1 | sampler chain: logits -> ?penalties -> ?dry -> ?top-n-sigma -> top-k -> ?typical -> top-p -> min-p -> ?xtc -> temp-ext -> dist
slot launch_slot_: id 3 | task 591 | processing task, is_child = 0
slot update_slots: id 3 | task 591 | new prompt, n_ctx_slot = 131072, n_keep = 0, task.n_tokens = 916
slot update_slots: id 3 | task 591 | n_past = 470, slot.prompt.tokens.size() = 1060, seq_id = 3, pos_min = 1059, n_swa = 1
slot update_slots: id 3 | task 591 | Checking checkpoint with [467, 467] against 469...
/llama.cpp/ggml/src/ggml-cuda/ggml-cuda.cu:98: ROCm error
ROCm error: an illegal memory access was encountered
current device: -1, in function ggml_backend_cuda_buffer_set_tensor at /llama.cpp/ggml/src/ggml-cuda/ggml-cuda.cu:648
hipMemcpyAsync((char *)tensor->data + offset, data, size, hipMemcpyHostToDevice, ((hipStream_t)2))

Not sure if this is a llama-server issue or not, but have test many models and this is the only one with a ROCm error.

Model: Qwen3.5-35B-A3B-Q4_K_M

Linux Mint 22.3 kernel 6.17

Package: rocm-libs
Version: 7.2.0.70200-43~24.04

SA System Attributes

Runtime Version: 1.18
Runtime Ext Version: 1.15
System Timestamp Freq.: 1000.000000MHz
Sig. Max Wait Duration: 18446744073709551615 (0xFFFFFFFFFFFFFFFF) (timestamp count)
Machine Model: LARGE
System Endianness: LITTLE
Mwaitx: DISABLED
XNACK enabled: NO
DMAbuf Support: YES
VMM Support: YES

==========
HSA Agents

Agent 1

Name: AMD Ryzen 7 5700X 8-Core Processor
Uuid: CPU-XX

Agent 2

Name: gfx1200
Marketing Name: AMD Radeon RX 9060 XT

Agent 3

Name: gfx1200
Marketing Name: AMD Radeon RX 9060 XT

jwallgood changed discussion status to closed Mar 17

jwallgood changed discussion status to open Mar 17

jwallgood

Mar 20

All of the versions of this model that I have loaded, have the same invalid memory access issue. I have tried about 10 so far, and these are only ones with issues.
Qwen3.5-35B-A3B-Q4_K_M.gguf
Qwen3.5-35B-A3B-UD-Q4_K_XL.gguf
Qwen3.5-35B-A3B-Q5_K_S.gguf
Qwen3.5-35B-A3B-Q5_K_M.gguf

I have been running this model for several days, all day, every day, no issues
Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled.i1-Q4_K_M

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment

New to all things HF and AI, but bugs I am familiar with. ROCm: illegal memory access. Model: Qwen3.5-35B-A3B-Q4_K_M

SA System Attributes

==========HSA Agents

==========
HSA Agents