Instructions to use mradermacher/Qwen3.5-4B-Base-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mradermacher/Qwen3.5-4B-Base-GGUF with Transformers:

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("mradermacher/Qwen3.5-4B-Base-GGUF", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use mradermacher/Qwen3.5-4B-Base-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 mradermacher/Qwen3.5-4B-Base-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf mradermacher/Qwen3.5-4B-Base-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf mradermacher/Qwen3.5-4B-Base-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf mradermacher/Qwen3.5-4B-Base-GGUF:Q4_K_M

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 mradermacher/Qwen3.5-4B-Base-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf mradermacher/Qwen3.5-4B-Base-GGUF:Q4_K_M

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 mradermacher/Qwen3.5-4B-Base-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf mradermacher/Qwen3.5-4B-Base-GGUF:Q4_K_M

Use Docker

docker model run hf.co/mradermacher/Qwen3.5-4B-Base-GGUF:Q4_K_M

LM Studio
Jan
Ollama
How to use mradermacher/Qwen3.5-4B-Base-GGUF with Ollama:
```
ollama run hf.co/mradermacher/Qwen3.5-4B-Base-GGUF:Q4_K_M
```
Unsloth Desktop

How to use mradermacher/Qwen3.5-4B-Base-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf mradermacher/Qwen3.5-4B-Base-GGUF:Q4_K_M

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": "mradermacher/Qwen3.5-4B-Base-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use mradermacher/Qwen3.5-4B-Base-GGUF with Docker Model Runner:
```
docker model run hf.co/mradermacher/Qwen3.5-4B-Base-GGUF:Q4_K_M
```

Lemonade

How to use mradermacher/Qwen3.5-4B-Base-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull mradermacher/Qwen3.5-4B-Base-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Qwen3.5-4B-Base-GGUF-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use mradermacher/Qwen3.5-4B-Base-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 mradermacher/Qwen3.5-4B-Base-GGUF:Q4_K_M

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 mradermacher/Qwen3.5-4B-Base-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use mradermacher/Qwen3.5-4B-Base-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf mradermacher/Qwen3.5-4B-Base-GGUF:Q4_K_M

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 "mradermacher/Qwen3.5-4B-Base-GGUF:Q4_K_M" \
  --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"

mradermacher commited on Apr 24

Commit

d4ad9c6

verified ·

1 Parent(s): 611e9b4

uploaded from nico1

Browse files

Files changed (13) hide show

.gitattributes +12 -0
Qwen3.5-4B-Base.IQ4_XS.gguf +3 -0
Qwen3.5-4B-Base.Q2_K.gguf +3 -0
Qwen3.5-4B-Base.Q3_K_L.gguf +3 -0
Qwen3.5-4B-Base.Q3_K_M.gguf +3 -0
Qwen3.5-4B-Base.Q3_K_S.gguf +3 -0
Qwen3.5-4B-Base.Q4_K_M.gguf +3 -0
Qwen3.5-4B-Base.Q4_K_S.gguf +3 -0
Qwen3.5-4B-Base.Q5_K_M.gguf +3 -0
Qwen3.5-4B-Base.Q5_K_S.gguf +3 -0
Qwen3.5-4B-Base.Q6_K.gguf +3 -0
Qwen3.5-4B-Base.Q8_0.gguf +3 -0
Qwen3.5-4B-Base.f16.gguf +3 -0

@@ -35,3 +35,15 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
 Qwen3.5-4B-Base.mmproj-f16.gguf filter=lfs diff=lfs merge=lfs -text
 Qwen3.5-4B-Base.mmproj-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text

 *tfevents* filter=lfs diff=lfs merge=lfs -text
 Qwen3.5-4B-Base.mmproj-f16.gguf filter=lfs diff=lfs merge=lfs -text
 Qwen3.5-4B-Base.mmproj-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen3.5-4B-Base.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen3.5-4B-Base.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen3.5-4B-Base.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen3.5-4B-Base.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen3.5-4B-Base.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen3.5-4B-Base.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen3.5-4B-Base.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen3.5-4B-Base.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen3.5-4B-Base.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen3.5-4B-Base.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen3.5-4B-Base.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen3.5-4B-Base.f16.gguf filter=lfs diff=lfs merge=lfs -text

+version https://git-lfs.github.com/spec/v1
+oid sha256:ef24b31f10d49fa49acea2a476fd6f9975cdc7c13c46e1b84cbde965d8a2d0e0
+size 2529031168

+version https://git-lfs.github.com/spec/v1
+oid sha256:8ca8d27f8b5735c21d8cbff204c4fccfe0fbbbefce7e46ccdda69f2a743554fd
+size 1915470848

+version https://git-lfs.github.com/spec/v1
+oid sha256:c168e79ff82867ee3975b85220a4dcb35536dadeb8bfbe9b5d45184df413fa03
+size 2421316608

+version https://git-lfs.github.com/spec/v1
+oid sha256:75c6b14613527ccd54569fb37afd8348f7bc0ff48cfaa70d6b7deaaedea3160e
+size 2262064128

+version https://git-lfs.github.com/spec/v1
+oid sha256:5d628ba85c0231b3f3854333e54989fb2ae70fa93b8fad2d598c803de947a125
+size 2069879808

+version https://git-lfs.github.com/spec/v1
+oid sha256:1be1aecf1a4df0bffa3d48e53df111714a6632b9d835115af996d7b95185eb29
+size 2708804608

+version https://git-lfs.github.com/spec/v1
+oid sha256:e5a3bd961ee1e47241b29fbe782d4a7467e7842a633702a12cef284c1e25fec7
+size 2563888128

+version https://git-lfs.github.com/spec/v1
+oid sha256:f3da1af8ec9e7c40f57a29a3c43a061443deb23697bf703d2c60c7ec69ea81d8
+size 3074987008

+version https://git-lfs.github.com/spec/v1
+oid sha256:7a5b04a171249e701f69e3f974c559acdba2bb43c057292e16b862d2b608c01b
+size 2990035968

+version https://git-lfs.github.com/spec/v1
+oid sha256:c7f3ad4d46b2e4cbac22861d85fbf99a5abf2289b4f33448b92eb622ad6ae414
+size 3464055808

	@@ -0,0 +1,3 @@

	@@ -0,0 +1,3 @@

	@@ -0,0 +1,3 @@

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:2a5266475777daf23e21991592a006f6dbc0be4620ac6a12d7d57240b0027711
+size 4482403328

+version https://git-lfs.github.com/spec/v1
+oid sha256:6de6175fd0a289018cd88b1f415260dde6cd5ed6563cb467900fa86dc22b6227
+size 8424393728