Instructions to use MetaphoricalCode/QwQ-32B-Snowdrop-v0-exl3-5bpw-hb6 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use MetaphoricalCode/QwQ-32B-Snowdrop-v0-exl3-5bpw-hb6 with Transformers:

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

pipe = pipeline("text-generation", model="MetaphoricalCode/QwQ-32B-Snowdrop-v0-exl3-5bpw-hb6")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("MetaphoricalCode/QwQ-32B-Snowdrop-v0-exl3-5bpw-hb6")
model = AutoModelForCausalLM.from_pretrained("MetaphoricalCode/QwQ-32B-Snowdrop-v0-exl3-5bpw-hb6", 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=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use MetaphoricalCode/QwQ-32B-Snowdrop-v0-exl3-5bpw-hb6 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "MetaphoricalCode/QwQ-32B-Snowdrop-v0-exl3-5bpw-hb6"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "MetaphoricalCode/QwQ-32B-Snowdrop-v0-exl3-5bpw-hb6",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/MetaphoricalCode/QwQ-32B-Snowdrop-v0-exl3-5bpw-hb6

SGLang

How to use MetaphoricalCode/QwQ-32B-Snowdrop-v0-exl3-5bpw-hb6 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 "MetaphoricalCode/QwQ-32B-Snowdrop-v0-exl3-5bpw-hb6" \
    --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": "MetaphoricalCode/QwQ-32B-Snowdrop-v0-exl3-5bpw-hb6",
		"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 "MetaphoricalCode/QwQ-32B-Snowdrop-v0-exl3-5bpw-hb6" \
        --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": "MetaphoricalCode/QwQ-32B-Snowdrop-v0-exl3-5bpw-hb6",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use MetaphoricalCode/QwQ-32B-Snowdrop-v0-exl3-5bpw-hb6 with Docker Model Runner:
```
docker model run hf.co/MetaphoricalCode/QwQ-32B-Snowdrop-v0-exl3-5bpw-hb6
```

MetaphoricalCode commited on Jun 7, 2025

Commit

ac77ec7

verified ·

1 Parent(s): 333a58f

Proper bos_token_id

Browse files

Files changed (2) hide show

README.md +2 -0
config.json +2 -2

README.md CHANGED Viewed

@@ -8,6 +8,8 @@ tags:
 - mergekitty
 - merge
 ---
 ## Quantized using the default exllamav3 (0.0.1) quantization process.
 - Original model: https://huggingface.co/trashpanda-org/QwQ-32B-Snowdrop-v0

 - mergekitty
 - merge
 ---
+# UPDATE: 07.06.2025
+- Proper bos_token_id was uploaded. Download the new config.json file for the model to work properly!
 ## Quantized using the default exllamav3 (0.0.1) quantization process.
 - Original model: https://huggingface.co/trashpanda-org/QwQ-32B-Snowdrop-v0

config.json CHANGED Viewed

@@ -5,7 +5,7 @@
     ],
     "attention_dropout": 0.0,
     "bos_token_id": 151643,
-    "eos_token_id": 151643,
     "hidden_act": "silu",
     "hidden_size": 5120,
     "initializer_range": 0.02,
@@ -29,7 +29,7 @@
     "quantization_config": {
         "quant_method": "exl3",
         "version": "0.0.1",
-        "bits": 5.0,
         "head_bits": 6,
         "calibration": {
             "rows": 100,

     ],
     "attention_dropout": 0.0,
     "bos_token_id": 151643,
+    "eos_token_id": 151645,
     "hidden_act": "silu",
     "hidden_size": 5120,
     "initializer_range": 0.02,
     "quantization_config": {
         "quant_method": "exl3",
         "version": "0.0.1",
+        "bits": 4.0,
         "head_bits": 6,
         "calibration": {
             "rows": 100,