Instructions to use JunHowie/Qwen3-30B-A3B-GPTQ-Int4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use JunHowie/Qwen3-30B-A3B-GPTQ-Int4 with Transformers:

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

pipe = pipeline("text-generation", model="JunHowie/Qwen3-30B-A3B-GPTQ-Int4")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("JunHowie/Qwen3-30B-A3B-GPTQ-Int4")
model = AutoModelForCausalLM.from_pretrained("JunHowie/Qwen3-30B-A3B-GPTQ-Int4", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use JunHowie/Qwen3-30B-A3B-GPTQ-Int4 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "JunHowie/Qwen3-30B-A3B-GPTQ-Int4"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "JunHowie/Qwen3-30B-A3B-GPTQ-Int4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/JunHowie/Qwen3-30B-A3B-GPTQ-Int4

SGLang

How to use JunHowie/Qwen3-30B-A3B-GPTQ-Int4 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 "JunHowie/Qwen3-30B-A3B-GPTQ-Int4" \
    --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": "JunHowie/Qwen3-30B-A3B-GPTQ-Int4",
		"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 "JunHowie/Qwen3-30B-A3B-GPTQ-Int4" \
        --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": "JunHowie/Qwen3-30B-A3B-GPTQ-Int4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use JunHowie/Qwen3-30B-A3B-GPTQ-Int4 with Docker Model Runner:
```
docker model run hf.co/JunHowie/Qwen3-30B-A3B-GPTQ-Int4
```

JunHowie commited on Sep 6, 2025

Commit

6b72584

verified ·

1 Parent(s): bb4e724

Update config.json

Browse files

Files changed (1) hide show

config.json +9 -26

config.json CHANGED Viewed

@@ -24,31 +24,6 @@
   "num_hidden_layers": 48,
   "num_key_value_heads": 4,
   "output_router_logits": false,
-  "quantization_config": {
-    "modules_to_not_convert": [".mlp.gate"],
-    "bits": 4,
-    "checkpoint_format": "gptq",
-    "desc_act": false,
-    "group_size": 128,
-    "hyb_act": false,
-    "lm_head": false,
-    "meta": {
-      "damp_auto_increment": 0.01,
-      "damp_percent": 0.05,
-      "mse": 0.0,
-      "quantizer": [
-        "gptqmodel:4.0.0"
-      ],
-      "static_groups": false,
-      "true_sequential": true,
-      "uri": "https://github.com/modelcloud/gptqmodel",
-      "v2": false,
-      "v2_alpha": 0.25
-    },
-    "pack_dtype": "int32",
-    "quant_method": "gptq",
-    "sym": true
-  },
   "rms_norm_eps": 1e-06,
   "rope_scaling": null,
   "rope_theta": 1000000.0,
@@ -59,5 +34,13 @@
   "transformers_version": "4.55.4",
   "use_cache": true,
   "use_sliding_window": false,
-  "vocab_size": 151936
 }

   "num_hidden_layers": 48,
   "num_key_value_heads": 4,
   "output_router_logits": false,
   "rms_norm_eps": 1e-06,
   "rope_scaling": null,
   "rope_theta": 1000000.0,
   "transformers_version": "4.55.4",
   "use_cache": true,
   "use_sliding_window": false,
+  "vocab_size": 151936,
+  "quantization_config": {
+    "bits": 4,
+    "checkpoint_format": "gptq",
+    "desc_act": false,
+    "group_size": 128,
+    "hyb_act": false,
+    "lm_head": false
+  }
 }