Instructions to use bknyaz/Qwen3-Coder-Next-REAM with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use bknyaz/Qwen3-Coder-Next-REAM with Transformers:

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

pipe = pipeline("text-generation", model="bknyaz/Qwen3-Coder-Next-REAM")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("bknyaz/Qwen3-Coder-Next-REAM")
model = AutoModelForCausalLM.from_pretrained("bknyaz/Qwen3-Coder-Next-REAM")
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

vLLM

How to use bknyaz/Qwen3-Coder-Next-REAM with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/bknyaz/Qwen3-Coder-Next-REAM

SGLang

How to use bknyaz/Qwen3-Coder-Next-REAM 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 "bknyaz/Qwen3-Coder-Next-REAM" \
    --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": "bknyaz/Qwen3-Coder-Next-REAM",
		"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 "bknyaz/Qwen3-Coder-Next-REAM" \
        --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": "bknyaz/Qwen3-Coder-Next-REAM",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use bknyaz/Qwen3-Coder-Next-REAM with Docker Model Runner:
```
docker model run hf.co/bknyaz/Qwen3-Coder-Next-REAM
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

arXiv: REAM: Merging Improves Pruning of Experts in LLMs

Qwen3-Coder-Next-REAM

This model is a compressed version of Qwen/Qwen3-Coder-Next. It is obtained by reducing the number of experts in each MoE layer from 512 to 384. This reduction is achieved by the REAM method described in https://bknyaz.github.io/blog/2026/moe/.

Compared to other models obtained in this collection, more code data is used in the calibration data during pruning/merging to better preserve original's model coding abilities. Specifically, the ratio between c4, math and coding data (see https://bknyaz.github.io/blog/2026/moe/) is 0.0, 0.3, 0.7. The calibration data used here is the same as in Qwen3-Coder-Next-REAP. Compared to other REAM models, here we used C=32 (number of experts in groups) instead of C=16, which we found to work better.

The compressed model has 60B params (120GB) instead of 80B (160GB) of the original model, reducing storage and GPU memory requirements by roughly 25%. At the same time, the model retains 100% (or very close) of the original model's performance on a variety of benchmarks (see Results section below). Additional efficiency optimization (e.g., quantization) can be added similarly to the original model.

See additional details at Qwen3-30B-A3B-Instruct-2507-REAM.