Instructions to use mradermacher/Orion-Qwen3-4B-SFT-v2605-i1-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mradermacher/Orion-Qwen3-4B-SFT-v2605-i1-GGUF with Transformers:

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("mradermacher/Orion-Qwen3-4B-SFT-v2605-i1-GGUF", dtype="auto")

llama-cpp-python

How to use mradermacher/Orion-Qwen3-4B-SFT-v2605-i1-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="mradermacher/Orion-Qwen3-4B-SFT-v2605-i1-GGUF",
	filename="Orion-Qwen3-4B-SFT-v2605.i1-IQ1_M.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use mradermacher/Orion-Qwen3-4B-SFT-v2605-i1-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/Orion-Qwen3-4B-SFT-v2605-i1-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf mradermacher/Orion-Qwen3-4B-SFT-v2605-i1-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/Orion-Qwen3-4B-SFT-v2605-i1-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf mradermacher/Orion-Qwen3-4B-SFT-v2605-i1-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/Orion-Qwen3-4B-SFT-v2605-i1-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf mradermacher/Orion-Qwen3-4B-SFT-v2605-i1-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/Orion-Qwen3-4B-SFT-v2605-i1-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf mradermacher/Orion-Qwen3-4B-SFT-v2605-i1-GGUF:Q4_K_M

Use Docker

docker model run hf.co/mradermacher/Orion-Qwen3-4B-SFT-v2605-i1-GGUF:Q4_K_M

LM Studio
Jan
Ollama
How to use mradermacher/Orion-Qwen3-4B-SFT-v2605-i1-GGUF with Ollama:
```
ollama run hf.co/mradermacher/Orion-Qwen3-4B-SFT-v2605-i1-GGUF:Q4_K_M
```

Unsloth Studio

How to use mradermacher/Orion-Qwen3-4B-SFT-v2605-i1-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 mradermacher/Orion-Qwen3-4B-SFT-v2605-i1-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 mradermacher/Orion-Qwen3-4B-SFT-v2605-i1-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for mradermacher/Orion-Qwen3-4B-SFT-v2605-i1-GGUF to start chatting

How to use mradermacher/Orion-Qwen3-4B-SFT-v2605-i1-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/Orion-Qwen3-4B-SFT-v2605-i1-GGUF:Q4_K_M

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": "mradermacher/Orion-Qwen3-4B-SFT-v2605-i1-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use mradermacher/Orion-Qwen3-4B-SFT-v2605-i1-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/Orion-Qwen3-4B-SFT-v2605-i1-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/Orion-Qwen3-4B-SFT-v2605-i1-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use mradermacher/Orion-Qwen3-4B-SFT-v2605-i1-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/Orion-Qwen3-4B-SFT-v2605-i1-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/Orion-Qwen3-4B-SFT-v2605-i1-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"

Docker Model Runner
How to use mradermacher/Orion-Qwen3-4B-SFT-v2605-i1-GGUF with Docker Model Runner:
```
docker model run hf.co/mradermacher/Orion-Qwen3-4B-SFT-v2605-i1-GGUF:Q4_K_M
```

Lemonade

How to use mradermacher/Orion-Qwen3-4B-SFT-v2605-i1-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull mradermacher/Orion-Qwen3-4B-SFT-v2605-i1-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Orion-Qwen3-4B-SFT-v2605-i1-GGUF-Q4_K_M

List all available models

lemonade list

mradermacher commited on May 23

Commit

5743a2c

verified ·

1 Parent(s): d8772bd

uploaded from rich1

Browse files

Files changed (25) hide show

.gitattributes +24 -0
Orion-Qwen3-4B-SFT-v2605.i1-IQ1_M.gguf +3 -0
Orion-Qwen3-4B-SFT-v2605.i1-IQ1_S.gguf +3 -0
Orion-Qwen3-4B-SFT-v2605.i1-IQ2_M.gguf +3 -0
Orion-Qwen3-4B-SFT-v2605.i1-IQ2_S.gguf +3 -0
Orion-Qwen3-4B-SFT-v2605.i1-IQ2_XS.gguf +3 -0
Orion-Qwen3-4B-SFT-v2605.i1-IQ2_XXS.gguf +3 -0
Orion-Qwen3-4B-SFT-v2605.i1-IQ3_M.gguf +3 -0
Orion-Qwen3-4B-SFT-v2605.i1-IQ3_S.gguf +3 -0
Orion-Qwen3-4B-SFT-v2605.i1-IQ3_XS.gguf +3 -0
Orion-Qwen3-4B-SFT-v2605.i1-IQ3_XXS.gguf +3 -0
Orion-Qwen3-4B-SFT-v2605.i1-IQ4_NL.gguf +3 -0
Orion-Qwen3-4B-SFT-v2605.i1-IQ4_XS.gguf +3 -0
Orion-Qwen3-4B-SFT-v2605.i1-Q2_K.gguf +3 -0
Orion-Qwen3-4B-SFT-v2605.i1-Q2_K_S.gguf +3 -0
Orion-Qwen3-4B-SFT-v2605.i1-Q3_K_L.gguf +3 -0
Orion-Qwen3-4B-SFT-v2605.i1-Q3_K_M.gguf +3 -0
Orion-Qwen3-4B-SFT-v2605.i1-Q3_K_S.gguf +3 -0
Orion-Qwen3-4B-SFT-v2605.i1-Q4_0.gguf +3 -0
Orion-Qwen3-4B-SFT-v2605.i1-Q4_1.gguf +3 -0
Orion-Qwen3-4B-SFT-v2605.i1-Q4_K_M.gguf +3 -0
Orion-Qwen3-4B-SFT-v2605.i1-Q4_K_S.gguf +3 -0
Orion-Qwen3-4B-SFT-v2605.i1-Q5_K_M.gguf +3 -0
Orion-Qwen3-4B-SFT-v2605.i1-Q5_K_S.gguf +3 -0
Orion-Qwen3-4B-SFT-v2605.i1-Q6_K.gguf +3 -0

.gitattributes CHANGED Viewed

@@ -34,3 +34,27 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
 Orion-Qwen3-4B-SFT-v2605.imatrix.gguf filter=lfs diff=lfs merge=lfs -text

 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
 Orion-Qwen3-4B-SFT-v2605.imatrix.gguf filter=lfs diff=lfs merge=lfs -text
+Orion-Qwen3-4B-SFT-v2605.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text
+Orion-Qwen3-4B-SFT-v2605.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text
+Orion-Qwen3-4B-SFT-v2605.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text
+Orion-Qwen3-4B-SFT-v2605.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text
+Orion-Qwen3-4B-SFT-v2605.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text
+Orion-Qwen3-4B-SFT-v2605.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text
+Orion-Qwen3-4B-SFT-v2605.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text
+Orion-Qwen3-4B-SFT-v2605.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text
+Orion-Qwen3-4B-SFT-v2605.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text
+Orion-Qwen3-4B-SFT-v2605.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text
+Orion-Qwen3-4B-SFT-v2605.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text
+Orion-Qwen3-4B-SFT-v2605.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text
+Orion-Qwen3-4B-SFT-v2605.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+Orion-Qwen3-4B-SFT-v2605.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Orion-Qwen3-4B-SFT-v2605.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+Orion-Qwen3-4B-SFT-v2605.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Orion-Qwen3-4B-SFT-v2605.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Orion-Qwen3-4B-SFT-v2605.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+Orion-Qwen3-4B-SFT-v2605.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text
+Orion-Qwen3-4B-SFT-v2605.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Orion-Qwen3-4B-SFT-v2605.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Orion-Qwen3-4B-SFT-v2605.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Orion-Qwen3-4B-SFT-v2605.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Orion-Qwen3-4B-SFT-v2605.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text

Orion-Qwen3-4B-SFT-v2605.i1-IQ1_M.gguf ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:e72d5bf3c5fa0c21cd01cf679e0a219d29c37ba8e89b7e93d390350bdaa0c848
+size 1127018464

Orion-Qwen3-4B-SFT-v2605.i1-IQ1_S.gguf ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:6c1691c31812b1ca3ce7e4e513f04351c84af367fda2003d45da2baae937b879
+size 1055256544

Orion-Qwen3-4B-SFT-v2605.i1-IQ2_M.gguf ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:e276b44e3d6cf7401c52a8e26c4723d9310de5b5c292d82a62c4532611f86e40
+size 1512984544

Orion-Qwen3-4B-SFT-v2605.i1-IQ2_S.gguf ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:62542b503ea65f4aeea9012861f7f60d280253c5f8f76c12ed690c0e75b76632
+size 1417301984

Orion-Qwen3-4B-SFT-v2605.i1-IQ2_XS.gguf ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:8500d959fb6713762756c1b74eae9140eef81fe6da9871027507415a649e0870
+size 1354100704

Orion-Qwen3-4B-SFT-v2605.i1-IQ2_XXS.gguf ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:c72d13936fd5cde70f4bbe5338738ab2b512b9770df841e83da125319245a18a
+size 1246621664

Orion-Qwen3-4B-SFT-v2605.i1-IQ3_M.gguf ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:6adaa5fd73da6293a8965d8ad3291869dc321076208eb8a515639734ca0b5e4e
+size 1962896864

Orion-Qwen3-4B-SFT-v2605.i1-IQ3_S.gguf ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:595015a793b3aa6e016d3ee591eff9f56f7b6761b25a540d3ab64c84e22a658f
+size 1899531744

Orion-Qwen3-4B-SFT-v2605.i1-IQ3_XS.gguf ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:97e44a1684b5eee0da60c8a12a98d3f914f8d246e1e330d1b9fa008d5c4df7e8
+size 1814375904

Orion-Qwen3-4B-SFT-v2605.i1-IQ3_XXS.gguf ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:b990e31b4f55d274510f6ba3120b4b7bb108ab009f9e08aba928c0153ddc995e
+size 1670189024

Orion-Qwen3-4B-SFT-v2605.i1-IQ4_NL.gguf ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:3abf0e14dd0004d0dafb0182cb219e1a30ac396f322411424d61b0d9a9a98b6b
+size 2381344224

Orion-Qwen3-4B-SFT-v2605.i1-IQ4_XS.gguf ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:a2b07119f379f18c59a013e4da64268f4e29785a3b10bd5ec88b48cb4716334d
+size 2270752224

Orion-Qwen3-4B-SFT-v2605.i1-Q2_K.gguf ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:81b8cca0590d5a96b2cb6c993b0f865095f76d165604f2771fec502161e346c1
+size 1669500384

Orion-Qwen3-4B-SFT-v2605.i1-Q2_K_S.gguf ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:8cd90f9ea850822f18c9e3a6cba750bae0ac898da2322bc54de93a64b3af63be
+size 1563454944

Orion-Qwen3-4B-SFT-v2605.i1-Q3_K_L.gguf ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:f080a03aa4cacaa8291ecf0ca7ccb4f781566f5b292216684b345cefe5effcf9
+size 2239786464

Orion-Qwen3-4B-SFT-v2605.i1-Q3_K_M.gguf ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:43fa515da32941a4097d4ef074a221b44215197888ae6b351dcc645c3be654cf
+size 2075618784

Orion-Qwen3-4B-SFT-v2605.i1-Q3_K_S.gguf ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:7d1d695e58d999ac35caa28858cd751f378f3b9d4cb113a9ca8160bc578c495b
+size 1886997984

Orion-Qwen3-4B-SFT-v2605.i1-Q4_0.gguf ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:f5658b970ac189ea9b38b6b8306e11e8e7d855cc9ac8a33de1678eda1694bf7a
+size 2375773664

Orion-Qwen3-4B-SFT-v2605.i1-Q4_1.gguf ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:30fadb3b5c65b2a58041599ebf38f79b09061a2d68fa07417c482eac6b67febe
+size 2596629984

Orion-Qwen3-4B-SFT-v2605.i1-Q4_K_M.gguf ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:bdd409e62253d530692f22d904ff0d61b8570dcf05bbff0aafdce869d665b378
+size 2497281504

Orion-Qwen3-4B-SFT-v2605.i1-Q4_K_S.gguf ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:31df8e96637df3a13ab96203c0e695f320a10a5160e0e6b5608364f026238586
+size 2383310304

Orion-Qwen3-4B-SFT-v2605.i1-Q5_K_M.gguf ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:8e4d625fc87f776e9f1ab2a16306d4ddcab515c4d52b865d20f87ca8928a96a2
+size 2889514464

Orion-Qwen3-4B-SFT-v2605.i1-Q5_K_S.gguf ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:5a82c8b3e107c38a3554ea60e7fdce93a9d37659b60dcd54362826c494b7631e
+size 2823712224

Orion-Qwen3-4B-SFT-v2605.i1-Q6_K.gguf ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:feac6ef460f13aac4fd94e619384dbe435611d66aef1d7b8bcdb1532a5aea84b
+size 3306261984