Instructions to use Akicou/Qwen3.8-Flash-Next-REAM-60Pct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Akicou/Qwen3.8-Flash-Next-REAM-60Pct with Transformers:

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

pipe = pipeline("text-generation", model="Akicou/Qwen3.8-Flash-Next-REAM-60Pct")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Akicou/Qwen3.8-Flash-Next-REAM-60Pct")
model = AutoModelForCausalLM.from_pretrained("Akicou/Qwen3.8-Flash-Next-REAM-60Pct", 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 Akicou/Qwen3.8-Flash-Next-REAM-60Pct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Akicou/Qwen3.8-Flash-Next-REAM-60Pct"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Akicou/Qwen3.8-Flash-Next-REAM-60Pct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Akicou/Qwen3.8-Flash-Next-REAM-60Pct

SGLang

How to use Akicou/Qwen3.8-Flash-Next-REAM-60Pct 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 "Akicou/Qwen3.8-Flash-Next-REAM-60Pct" \
    --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": "Akicou/Qwen3.8-Flash-Next-REAM-60Pct",
		"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 "Akicou/Qwen3.8-Flash-Next-REAM-60Pct" \
        --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": "Akicou/Qwen3.8-Flash-Next-REAM-60Pct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Akicou/Qwen3.8-Flash-Next-REAM-60Pct with Docker Model Runner:
```
docker model run hf.co/Akicou/Qwen3.8-Flash-Next-REAM-60Pct
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Qwen3.8-Flash-Next-REAM-60Pct

REAM-compressed version of Qwen/Qwen3.8-Flash-Next, produced with Akicou/ream, a REAM/REAP-style MoE compression framework.

Method

Router Expert Activation Merging (REAM). The model is calibrated on the built-in hardcoded prompt set, then experts are grouped by gated similarity (half hidden-state, half router distribution) and merged with saliency-weighted averaging. 40% of the routed experts are removed, so each layer goes from 512 experts down to 308. The router is shrunk to match, keeping only the centroid rows.

Shared experts, attention, n-gram embeddings, and dense layers are left untouched. Only routed experts are merged.

How it was created

python examples/compress_sequential.py \
    --model Qwen/Qwen3.8-Flash-Next \
    --output ./qwen4-ream-60 \
    --target-ratio 0.60 \
    --samples 100 \
    --max-seq-len 512 \
    --batch-size 4 \
    --max-tokens 2048 \
    --cpu-merge \
    --fast-merge \
    --seed 42

Hardware: 6× NVIDIA H100 SXM 80GB

Note

This is an experimental release. It has not been benchmarked. The model uses trust_remote_code=True, same as the base model.

Basic usage

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "Akicou/Qwen3.8-Flash-Next-REAM-60Pct"

tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    torch_dtype=torch.bfloat16,
    device_map="auto",
    trust_remote_code=True,
)

prompt = "Explain the concept of reinforcement learning."
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)

with torch.no_grad():
    output = model.generate(**inputs, max_new_tokens=128, do_sample=False)

print(tokenizer.decode(output[0], skip_special_tokens=True))