Instructions to use roskosmos19/Rhea-4B-fast-0409 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use roskosmos19/Rhea-4B-fast-0409 with Transformers:

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

pipe = pipeline("text-generation", model="roskosmos19/Rhea-4B-fast-0409")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("roskosmos19/Rhea-4B-fast-0409")
model = AutoModelForCausalLM.from_pretrained("roskosmos19/Rhea-4B-fast-0409", 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 roskosmos19/Rhea-4B-fast-0409 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "roskosmos19/Rhea-4B-fast-0409"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "roskosmos19/Rhea-4B-fast-0409",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/roskosmos19/Rhea-4B-fast-0409

SGLang

How to use roskosmos19/Rhea-4B-fast-0409 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 "roskosmos19/Rhea-4B-fast-0409" \
    --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": "roskosmos19/Rhea-4B-fast-0409",
		"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 "roskosmos19/Rhea-4B-fast-0409" \
        --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": "roskosmos19/Rhea-4B-fast-0409",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use roskosmos19/Rhea-4B-fast-0409 with Docker Model Runner:
```
docker model run hf.co/roskosmos19/Rhea-4B-fast-0409
```

Rhea-4B-Agentic

Faster • Cheaper • Stronger for agentic & coding tasks

Optimized successor of the original Rhea-4B-Coding / Athenea line.

What changed for better price/performance

Aspect	Original multi-pass Rhea	Rhea-4B-Agentic (this)
Reasoning style	Forced 3-pass (implement→review→final)	Single-pass + optional `<think>`
Context	262k	32 768 (covers real agent workloads)
Forced long outputs	min_new_tokens=1024	Removed – answers as long as needed
Special tokens	Broken prefixes + many vision	Clean + lean (tools + thinking only)
Generation defaults	High temp / long forced	Tuned 0.4 / 0.9 for quality + speed
Agentic readiness	Good	Improved tool-calling template
Inference cost (VRAM/time)	Higher (long forced reasoning)	Significantly lower

→ Same 4B base intelligence, noticeably faster and cheaper to run, better real-world agentic behavior because it is no longer forced into three full generations.

Why this is better for agentic tasks

Standard <think>...</think> for chain-of-thought (optional, model decides when useful)
Clean, reliable tool-calling format
No artificial multi-pass overhead that multiplies latency and cost
Strong coding + reasoning focus retained
System prompt encourages precise, secure, efficient solutions

Technical specs

Architecture: Qwen3ForCausalLM (4B)
Context: 32 768 tokens
Special tokens: <|im_start|>, <|im_end|>, <think>, </think>, tool tags
Recommended quant: Q4_K_M / AWQ for best speed/quality

Recommended settings

{
  "temperature": 0.4,
  "top_p": 0.9,
  "top_k": 30,
  "repetition_penalty": 1.05,
  "max_new_tokens": 8192
}

Quickstart

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "./Rhea-4B-Agentic"

tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto"
)

messages = [
    {"role": "user", "content": "Write a secure Python function that validates JWT tokens and handles expiration gracefully."}
]

text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
inputs = tokenizer([text], return_tensors="pt").to(model.device)

outputs = model.generate(**inputs, max_new_tokens=2048)
print(tokenizer.decode(outputs[0][len(inputs.input_ids[0]):], skip_special_tokens=False))

Deployment tips (max cheapness)

vLLM / SGLang: --max-model-len 32768
llama.cpp: Q4_K_M or Q5_K_M
Keep context ≤ 16k–24k in production for optimal speed/VRAM

Credits

Base: Qwen3-4B + Athenea / Rhea coding lineage
Optimized for agentic use, single-pass thinking, lower cost

Apache 2.0

Downloads last month: 311