Instructions to use second-state/Qwen3-30B-A3B-Instruct-2507-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use second-state/Qwen3-30B-A3B-Instruct-2507-GGUF with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="second-state/Qwen3-30B-A3B-Instruct-2507-GGUF")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("second-state/Qwen3-30B-A3B-Instruct-2507-GGUF")
model = AutoModelForCausalLM.from_pretrained("second-state/Qwen3-30B-A3B-Instruct-2507-GGUF", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use second-state/Qwen3-30B-A3B-Instruct-2507-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 second-state/Qwen3-30B-A3B-Instruct-2507-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf second-state/Qwen3-30B-A3B-Instruct-2507-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 second-state/Qwen3-30B-A3B-Instruct-2507-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf second-state/Qwen3-30B-A3B-Instruct-2507-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 second-state/Qwen3-30B-A3B-Instruct-2507-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf second-state/Qwen3-30B-A3B-Instruct-2507-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 second-state/Qwen3-30B-A3B-Instruct-2507-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf second-state/Qwen3-30B-A3B-Instruct-2507-GGUF:Q4_K_M

Use Docker

docker model run hf.co/second-state/Qwen3-30B-A3B-Instruct-2507-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use second-state/Qwen3-30B-A3B-Instruct-2507-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "second-state/Qwen3-30B-A3B-Instruct-2507-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": "second-state/Qwen3-30B-A3B-Instruct-2507-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/second-state/Qwen3-30B-A3B-Instruct-2507-GGUF:Q4_K_M

SGLang

How to use second-state/Qwen3-30B-A3B-Instruct-2507-GGUF with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "second-state/Qwen3-30B-A3B-Instruct-2507-GGUF" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "second-state/Qwen3-30B-A3B-Instruct-2507-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "second-state/Qwen3-30B-A3B-Instruct-2507-GGUF" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "second-state/Qwen3-30B-A3B-Instruct-2507-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use second-state/Qwen3-30B-A3B-Instruct-2507-GGUF with Ollama:
```
ollama run hf.co/second-state/Qwen3-30B-A3B-Instruct-2507-GGUF:Q4_K_M
```

Unsloth Studio

How to use second-state/Qwen3-30B-A3B-Instruct-2507-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 second-state/Qwen3-30B-A3B-Instruct-2507-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 second-state/Qwen3-30B-A3B-Instruct-2507-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for second-state/Qwen3-30B-A3B-Instruct-2507-GGUF to start chatting

How to use second-state/Qwen3-30B-A3B-Instruct-2507-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf second-state/Qwen3-30B-A3B-Instruct-2507-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": "second-state/Qwen3-30B-A3B-Instruct-2507-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

OpenClaw new

How to use second-state/Qwen3-30B-A3B-Instruct-2507-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf second-state/Qwen3-30B-A3B-Instruct-2507-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 "second-state/Qwen3-30B-A3B-Instruct-2507-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 second-state/Qwen3-30B-A3B-Instruct-2507-GGUF with Docker Model Runner:
```
docker model run hf.co/second-state/Qwen3-30B-A3B-Instruct-2507-GGUF:Q4_K_M
```

Lemonade

How to use second-state/Qwen3-30B-A3B-Instruct-2507-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull second-state/Qwen3-30B-A3B-Instruct-2507-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Qwen3-30B-A3B-Instruct-2507-GGUF-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use second-state/Qwen3-30B-A3B-Instruct-2507-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 second-state/Qwen3-30B-A3B-Instruct-2507-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 second-state/Qwen3-30B-A3B-Instruct-2507-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

apepkuss79 commited on Jul 30, 2025

Commit

4c72b53

verified ·

1 Parent(s): 07d96bb

Update models

Browse files

Files changed (17) hide show

.gitattributes +15 -0
Qwen3-30B-A3B-Instruct-2507-Q2_K.gguf +3 -0
Qwen3-30B-A3B-Instruct-2507-Q3_K_L.gguf +3 -0
Qwen3-30B-A3B-Instruct-2507-Q3_K_M.gguf +3 -0
Qwen3-30B-A3B-Instruct-2507-Q3_K_S.gguf +3 -0
Qwen3-30B-A3B-Instruct-2507-Q4_0.gguf +3 -0
Qwen3-30B-A3B-Instruct-2507-Q4_K_M.gguf +3 -0
Qwen3-30B-A3B-Instruct-2507-Q4_K_S.gguf +3 -0
Qwen3-30B-A3B-Instruct-2507-Q5_0.gguf +3 -0
Qwen3-30B-A3B-Instruct-2507-Q5_K_M.gguf +3 -0
Qwen3-30B-A3B-Instruct-2507-Q5_K_S.gguf +3 -0
Qwen3-30B-A3B-Instruct-2507-Q6_K.gguf +3 -0
Qwen3-30B-A3B-Instruct-2507-Q8_0.gguf +3 -0
Qwen3-30B-A3B-Instruct-2507-f16-00001-of-00003.gguf +3 -0
Qwen3-30B-A3B-Instruct-2507-f16-00002-of-00003.gguf +3 -0
Qwen3-30B-A3B-Instruct-2507-f16-00003-of-00003.gguf +3 -0
config.json +38 -0

@@ -33,3 +33,18 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text

 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+Qwen3-30B-A3B-Instruct-2507-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen3-30B-A3B-Instruct-2507-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen3-30B-A3B-Instruct-2507-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen3-30B-A3B-Instruct-2507-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen3-30B-A3B-Instruct-2507-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen3-30B-A3B-Instruct-2507-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen3-30B-A3B-Instruct-2507-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen3-30B-A3B-Instruct-2507-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen3-30B-A3B-Instruct-2507-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen3-30B-A3B-Instruct-2507-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen3-30B-A3B-Instruct-2507-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen3-30B-A3B-Instruct-2507-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen3-30B-A3B-Instruct-2507-f16-00001-of-00003.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen3-30B-A3B-Instruct-2507-f16-00002-of-00003.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen3-30B-A3B-Instruct-2507-f16-00003-of-00003.gguf filter=lfs diff=lfs merge=lfs -text

+{
+  "architectures": [
+    "Qwen3MoeForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "decoder_sparse_step": 1,
+  "eos_token_id": 151645,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 6144,
+  "max_position_embeddings": 262144,
+  "max_window_layers": 48,
+  "mlp_only_layers": [],
+  "model_type": "qwen3_moe",
+  "moe_intermediate_size": 768,
+  "norm_topk_prob": true,
+  "num_attention_heads": 32,
+  "num_experts": 128,
+  "num_experts_per_tok": 8,
+  "num_hidden_layers": 48,
+  "num_key_value_heads": 4,
+  "output_router_logits": false,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000000,
+  "router_aux_loss_coef": 0.001,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.51.0",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

+version https://git-lfs.github.com/spec/v1
+oid sha256:14d05b39366d80f952d884f65f267ec35ddb71911ec2a2b1ae85f93e58af1f5a
+size 11258609376

+version https://git-lfs.github.com/spec/v1
+oid sha256:1d26761cd9f53eafe582c45a68571b4f2a9a992a541b408050c739fdcfeceee6
+size 15900669664

+version https://git-lfs.github.com/spec/v1
+oid sha256:7d0964fd7dc1db4ce64dbad2c144d6546f4e9f7220f3fcb308a5c8814503d28a
+size 14711846624

+version https://git-lfs.github.com/spec/v1
+oid sha256:b63201a4210b4e683b0eb50161280edb0508f1d1fe565f5a744fb5f22bc3f125
+size 13292467936

+version https://git-lfs.github.com/spec/v1
+oid sha256:4a97d1ebf0a69d5ca44518a8a3bcb97a69d296270d77e371761039758a05dcf3
+size 17304489696

+version https://git-lfs.github.com/spec/v1
+oid sha256:0155f4523b0c2e3cb541abdc4b5b1845e7b74af9ae8ae8dde9f4d09783371c86
+size 18556686048

+version https://git-lfs.github.com/spec/v1
+oid sha256:01cc630cd0d10dc59036391348c839cc4a4245e31aaad8d10a2b6522e1a94f6d
+size 17456008928

+version https://git-lfs.github.com/spec/v1
+oid sha256:4a0af400feabb8c3b543e1b46ddf5bf3c09a1b587b24ed91f8e997e7a082cdae
+size 21080510176

+version https://git-lfs.github.com/spec/v1
+oid sha256:3373d7aa30bc7cfa2d0406254ba1f42f13e1f76aece21831a9f8681a0f3811ee
+size 21725581024

+version https://git-lfs.github.com/spec/v1
+oid sha256:4ebbc696c44e138b45ac6b234895556a899155519553f07180f0ebc990467097
+size 25092531936

	@@ -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 sha256:1e0e8ada2cb65e9ebbf9ea1a5c41f6323e0301d961adce268f8f40a006ccab94
+size 32483931872

+version https://git-lfs.github.com/spec/v1
+oid sha256:d4df355243d3b1991e0cbe97eb6f8a3e9467b4f349d88c4bc70699a74909f4b9
+size 29706750304

+version https://git-lfs.github.com/spec/v1
+oid sha256:418963816ce650f10969ef07dfe41382aa8501e33ad30f08b013f14ccf6ee378
+size 29557689440

+version https://git-lfs.github.com/spec/v1
+oid sha256:8672196692cdfff553ae3f903171d18d5246eb1be24ae0d832327e4f74bac60a
+size 1831363168