Instructions to use arcee-ai/Trinity-Mini-NVFP4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use arcee-ai/Trinity-Mini-NVFP4 with Transformers:

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

pipe = pipeline("text-generation", model="arcee-ai/Trinity-Mini-NVFP4", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("arcee-ai/Trinity-Mini-NVFP4", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("arcee-ai/Trinity-Mini-NVFP4", trust_remote_code=True)
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 arcee-ai/Trinity-Mini-NVFP4 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "arcee-ai/Trinity-Mini-NVFP4"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "arcee-ai/Trinity-Mini-NVFP4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/arcee-ai/Trinity-Mini-NVFP4

SGLang

How to use arcee-ai/Trinity-Mini-NVFP4 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 "arcee-ai/Trinity-Mini-NVFP4" \
    --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": "arcee-ai/Trinity-Mini-NVFP4",
		"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 "arcee-ai/Trinity-Mini-NVFP4" \
        --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": "arcee-ai/Trinity-Mini-NVFP4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use arcee-ai/Trinity-Mini-NVFP4 with Docker Model Runner:
```
docker model run hf.co/arcee-ai/Trinity-Mini-NVFP4
```

Trinity-Mini-NVFP4 / README.md

Anneketh Vij

Create README.md

1068478 verified about 2 months ago

preview code

raw

history blame contribute delete

4.12 kB

	---
	license: apache-2.0
	language:
	- en
	- es
	- fr
	- de
	- it
	- pt
	- ru
	- ar
	- hi
	- ko
	- zh
	library_name: transformers
	base_model:
	- arcee-ai/Trinity-Mini
	base_model_relation: quantized
	tags:
	- moe
	- nvfp4
	- modelopt
	- blackwell
	- vllm
	---
	<div align="center">
	<picture>
	<img
	src="https://cdn-uploads.huggingface.co/production/uploads/6435718aaaef013d1aec3b8b/i-v1KyAMOW_mgVGeic9WJ.png"
	alt="Arcee Trinity Mini"
	style="max-width: 100%; height: auto;"
	>
	</picture>
	</div>

	# Trinity Mini NVFP4

	This repository contains the NVFP4 quantized weights of Trinity-Mini for deployment on NVIDIA Blackwell GPUs.

	Trinity Mini is an Arcee AI 26B MoE model with 3B active parameters. It is the medium-sized model in our new Trinity family, a series of open-weight models for enterprise and tinkerers alike.

	This model is tuned for reasoning, but in testing, it uses a similar total token count to competitive instruction-tuned models.

	***

	Trinity Mini is trained on 10T tokens gathered and curated through a key partnership with [Datology](https://www.datologyai.com/), building upon the excellent dataset we used on [AFM-4.5B](https://huggingface.co/arcee-ai/AFM-4.5B) with additional math and code.

	Training was performed on a cluster of 512 H200 GPUs powered by [Prime Intellect](https://www.primeintellect.ai/) using HSDP parallelism.

	More details, including key architecture decisions, can be found on our blog [here](https://www.arcee.ai/blog/the-trinity-manifesto)

	***

	## Model Details

	* Model Architecture: AfmoeForCausalLM
	* Parameters: 26B, 3B active
	* Experts: 128 total, 8 active, 1 shared
	* Context length: 128k
	* Training Tokens: 10T
	* License: [Apache 2.0](https://huggingface.co/arcee-ai/Trinity-Mini#license)
	* Recommended settings:
	* temperature: 0.15
	* top_k: 50
	* top_p: 0.75
	* min_p: 0.06

	***

	## Benchmarks

	![](https://cdn-uploads.huggingface.co/production/uploads/6435718aaaef013d1aec3b8b/UMV0OZh_H1JfvgzBTXh6u.png)

	<div align="center">
	<picture>
	<img src="https://cdn-uploads.huggingface.co/production/uploads/6435718aaaef013d1aec3b8b/sSVjGNHfrJKmQ6w8I18ek.png" style="background-color:ghostwhite;padding:5px;" width="17%" alt="Powered by Datology">
	</picture>
	</div>

	## Quantization Details

	- Scheme: NVFP4 (`nvfp4_mlp_only` — MLP/expert weights only, attention remains BF16)
	- Tool: [NVIDIA ModelOpt](https://github.com/NVIDIA/Model-Optimizer)
	- Calibration: 512 samples, seq_length=2048, all-expert calibration enabled
	- KV cache: Not quantized

	## Running with vLLM

	Requires [vLLM](https://github.com/vllm-project/vllm) >= 0.18.0. Native FP4 compute requires Blackwell GPUs; older GPUs fall back to Marlin weight decompression automatically.

	### Blackwell GPUs (B200/B300/GB300) — Docker (recommended)

	```bash
	docker run --runtime nvidia --gpus all -p 8000:8000 \
	-v ~/.cache/huggingface:/root/.cache/huggingface \
	vllm/vllm-openai:v0.18.0-cu130 \
	arcee-ai/Trinity-Mini-NVFP4 \
	--trust-remote-code \
	--gpu-memory-utilization 0.90 \
	--max-model-len 8192
	```

	### Hopper GPUs (H100/H200) and others

	```bash
	vllm serve arcee-ai/Trinity-Mini-NVFP4 \
	--trust-remote-code \
	--gpu-memory-utilization 0.90 \
	--max-model-len 8192 \
	--host 0.0.0.0 \
	--port 8000
	```

	Note (Blackwell pip installs): If installing vLLM via pip on Blackwell rather than using Docker, native FP4 kernels may produce incorrect output due to package version mismatches. As a workaround, force the Marlin backend:

	```bash
	export VLLM_NVFP4_GEMM_BACKEND=marlin

	vllm serve arcee-ai/Trinity-Mini-NVFP4 \
	--trust-remote-code \
	--moe-backend marlin \
	--gpu-memory-utilization 0.90 \
	--max-model-len 8192 \
	--host 0.0.0.0 \
	--port 8000
	```

	Marlin decompresses FP4 weights to BF16 for compute, providing the full memory compression benefit (~3.7× vs BF16) but not native FP4 compute speedup. On Hopper GPUs (H100/H200), Marlin is selected automatically and no extra flags are needed.

	## License

	Trinity-Mini-NVFP4 is released under the Apache-2.0 license.