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

Libraries

How to use unsloth/Qwen3-30B-A3B-Base with Transformers:

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

pipe = pipeline("text-generation", model="unsloth/Qwen3-30B-A3B-Base")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("unsloth/Qwen3-30B-A3B-Base")
model = AutoModelForCausalLM.from_pretrained("unsloth/Qwen3-30B-A3B-Base")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use unsloth/Qwen3-30B-A3B-Base with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "unsloth/Qwen3-30B-A3B-Base"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "unsloth/Qwen3-30B-A3B-Base",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/unsloth/Qwen3-30B-A3B-Base

SGLang

How to use unsloth/Qwen3-30B-A3B-Base 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 "unsloth/Qwen3-30B-A3B-Base" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "unsloth/Qwen3-30B-A3B-Base",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "unsloth/Qwen3-30B-A3B-Base" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "unsloth/Qwen3-30B-A3B-Base",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Unsloth Studio new

How to use unsloth/Qwen3-30B-A3B-Base 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 unsloth/Qwen3-30B-A3B-Base 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 unsloth/Qwen3-30B-A3B-Base to start chatting

Using HuggingFace Spaces for Unsloth

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

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="unsloth/Qwen3-30B-A3B-Base",
    max_seq_length=2048,
)

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

danielhanchen commited on May 11, 2025

Commit

5ea9902

verified ·

1 Parent(s): 5998403

Add files using upload-large-folder tool

Browse files

Files changed (5) hide show

README.md +5 -3
added_tokens.json +4 -0
config.json +1 -1
tokenizer.json +2 -2
tokenizer_config.json +32 -0

README.md CHANGED Viewed

@@ -3,8 +3,10 @@ tags:
 - unsloth
 base_model:
 - Qwen/Qwen3-30B-A3B-Base
 ---
-# Qwen3-30B-A3B
 ## Qwen3 Highlights
@@ -18,9 +20,9 @@ Building upon extensive advancements in training data, model architecture, and o
 ## Model Overview
-**Qwen3-30B-A3B** has the following features:
 - Type: Causal Language Models
-- Training Stage: Pretraining & Post-training
 - Number of Parameters: 30.5B in total and 3.3B activated
 - Number of Paramaters (Non-Embedding): 29.9B
 - Number of Layers: 48

 - unsloth
 base_model:
 - Qwen/Qwen3-30B-A3B-Base
+license: apache-2.0
+library_name: transformers
 ---
+# Qwen3-30B-A3B-Base
 ## Qwen3 Highlights
 ## Model Overview
+**Qwen3-30B-A3B-Base** has the following features:
 - Type: Causal Language Models
+- Training Stage: Pretraining
 - Number of Parameters: 30.5B in total and 3.3B activated
 - Number of Paramaters (Non-Embedding): 29.9B
 - Number of Layers: 48

added_tokens.json CHANGED Viewed

@@ -1,6 +1,10 @@
 {
   "</tool_call>": 151658,
   "<tool_call>": 151657,
   "<|box_end|>": 151649,
   "<|box_start|>": 151648,
   "<|endoftext|>": 151643,

 {
+  "</think>": 151668,
   "</tool_call>": 151658,
+  "</tool_response>": 151666,
+  "<think>": 151667,
   "<tool_call>": 151657,
+  "<tool_response>": 151665,
   "<|box_end|>": 151649,
   "<|box_start|>": 151648,
   "<|endoftext|>": 151643,

config.json CHANGED Viewed

@@ -10,7 +10,7 @@
   "hidden_act": "silu",
   "hidden_size": 2048,
   "initializer_range": 0.02,
-  "intermediate_size": 8192,
   "max_position_embeddings": 32768,
   "max_window_layers": 48,
   "mlp_only_layers": [],

   "hidden_act": "silu",
   "hidden_size": 2048,
   "initializer_range": 0.02,
+  "intermediate_size": 6144,
   "max_position_embeddings": 32768,
   "max_window_layers": 48,
   "mlp_only_layers": [],

tokenizer.json CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
-size 11421896

 version https://git-lfs.github.com/spec/v1
+oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
+size 11422654

tokenizer_config.json CHANGED Viewed

@@ -177,6 +177,38 @@
       "rstrip": false,
       "single_word": false,
       "special": false
     }
   },
   "additional_special_tokens": [

       "rstrip": false,
       "single_word": false,
       "special": false
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
     }
   },
   "additional_special_tokens": [