Instructions to use maldv/QwentileLambda2.5-32B-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use maldv/QwentileLambda2.5-32B-Instruct with Transformers:

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

pipe = pipeline("text-generation", model="maldv/QwentileLambda2.5-32B-Instruct")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("maldv/QwentileLambda2.5-32B-Instruct")
model = AutoModelForCausalLM.from_pretrained("maldv/QwentileLambda2.5-32B-Instruct")
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]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use maldv/QwentileLambda2.5-32B-Instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "maldv/QwentileLambda2.5-32B-Instruct"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "maldv/QwentileLambda2.5-32B-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/maldv/QwentileLambda2.5-32B-Instruct

SGLang

How to use maldv/QwentileLambda2.5-32B-Instruct 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 "maldv/QwentileLambda2.5-32B-Instruct" \
    --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": "maldv/QwentileLambda2.5-32B-Instruct",
		"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 "maldv/QwentileLambda2.5-32B-Instruct" \
        --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": "maldv/QwentileLambda2.5-32B-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use maldv/QwentileLambda2.5-32B-Instruct with Docker Model Runner:
```
docker model run hf.co/maldv/QwentileLambda2.5-32B-Instruct
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

GGUF iMat IQ4_NL

Qwentile Λ 2.5 32B Instruct

Qwentile Λ 2.5 32B Instruct is a normalized denoised fourier interpolation of the following models:

output_base_model: "maldv/Qwentile2.5-32B-Instruct"
output_dtype: "bfloat16"
finetune_merge:
  - { "model": "a-m-team/AM-Thinking-v1", "base": "Qwen/Qwen2.5-32B", "alpha": 0.9 }
  - { "model": "nvidia/OpenCodeReasoning-Nemotron-32B", "base": "Qwen/Qwen2.5-32B", "alpha": 0.8, "is_input": true}
  - { "model": "maldv/Loqwqtus2.5-32B-Instruct", "base": "Qwen/Qwen2.5-32B", "alpha": 0.9 }
  - { "model": "trashpanda-org/QwQ-32B-Snowdrop-v0", "base": "Qwen/Qwen2.5-32B", "alpha": 0.9 }
  - { "model": "ArliAI/QwQ-32B-ArliAI-RpR-v3", "base": "Qwen/Qwen2.5-32B", "alpha": 0.8 }

In other words, all of these models get warped and interpolated in signal space, and then jammed back on top of the base model (which in this case was Qwentile2.5-32B-Instruct); but with the Nemotron OpenCodeReasoning input layer.

What is this?

The latest in my series of Qwen 2.5 merges. Some really good models have been released recently, so I folded them in with Qwentile as the base. It should exhibit superior thinking skills, and perhaps even some code ability. I was satisfied with QReasoner2.5-32B-Instruct for advanced reasoning, but I suspect this will be an improvement.

A <think> model?

No, oddly enough, given it's lineage I thought for sure it would be a thought model, but instead it blends thought with it's creative output almost seamlessly. The combination is pretty powerful in my initial tests.

Citation

If you find our work helpful, feel free to give us a cite.

@misc{qwentile-labmda-2.5-32b-instruct,
    title = {Qwentile Λ 2.5 32B Instruct},
    url = {https://huggingface.co/maldv/QwentileLambda2.5-32B-Instruct},
    author = {Praxis Maldevide},
    month = {May},
    year = {2025}
}

Downloads last month: 4

Safetensors

Model size

33B params

Tensor type

BF16

Model tree for maldv/QwentileLambda2.5-32B-Instruct

Base model

Qwen/Qwen2.5-32B

Finetuned

Qwen/QwQ-32B

Finetuned

ArliAI/QwQ-32B-ArliAI-RpR-v3

Finetuned

(2)

this model

Quantizations

3 models