Instructions to use dmnsh/Ornith-1.0-9B-NVFP4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use dmnsh/Ornith-1.0-9B-NVFP4 with Transformers:

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

pipe = pipeline("text-generation", model="dmnsh/Ornith-1.0-9B-NVFP4")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("dmnsh/Ornith-1.0-9B-NVFP4")
model = AutoModelForMultimodalLM.from_pretrained("dmnsh/Ornith-1.0-9B-NVFP4", device_map="auto")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.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(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use dmnsh/Ornith-1.0-9B-NVFP4 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "dmnsh/Ornith-1.0-9B-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": "dmnsh/Ornith-1.0-9B-NVFP4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/dmnsh/Ornith-1.0-9B-NVFP4

SGLang

How to use dmnsh/Ornith-1.0-9B-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 "dmnsh/Ornith-1.0-9B-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": "dmnsh/Ornith-1.0-9B-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 "dmnsh/Ornith-1.0-9B-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": "dmnsh/Ornith-1.0-9B-NVFP4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use dmnsh/Ornith-1.0-9B-NVFP4 with Docker Model Runner:
```
docker model run hf.co/dmnsh/Ornith-1.0-9B-NVFP4
```

Ornith-1.0-9B-NVFP4

NVFP4 / FP8 mixed-precision PTQ checkpoint of deepreinforce-ai/Ornith-1.0-9B, produced with NVIDIA TensorRT Model Optimizer (hf_ptq).

This is a community quantized derivative. All credit for the base model belongs to DeepReinforce. Please cite / attribute the upstream model when using this checkpoint.

Lineage

deepreinforce-ai/Ornith-1.0-9B   (BF16, Qwen3.5 hybrid VLM/LLM)
        │
        │  ModelOpt PTQ
        │  recipe: huggingface/qwen3_5/ptq/w4a16_nvfp4-fp8_attn-kv_fp8_cast
        ▼
dmnsh/Ornith-1.0-9B-NVFP4       (this repo)

Field	Value
Base model	`deepreinforce-ai/Ornith-1.0-9B`
Quantization tool	NVIDIA ModelOpt (`hf_ptq`)
Recipe	`huggingface/qwen3_5/ptq/w4a16_nvfp4-fp8_attn-kv_fp8_cast`
Calibration data	NVIDIA Nemotron SFT / science / math / coding / agentic mixes (ModelOpt default calib set)
License	MIT (inherits from base)

Quantization recipe (what changed)

From hf_quant_config.json:

Component	Format
MLP projections (`gate` / `up` / `down`)	W4A16 NVFP4 (group size 16)
Attention projections (full + linear attn)	FP8
KV cache	FP8
Vision tower (`model.visual.*`)	BF16 (not quantized)
`lm_head`	BF16 (excluded)

Top-level algo in the export config is MIXED_PRECISION (W4A16_NVFP4 + FP8).

Intended use

Same as the base Ornith model (agentic coding / reasoning), with lower memory and higher decode throughput on Blackwell GPUs (e.g. DGX Spark GB10). NVFP4 weight kernels need Blackwell; calibration can be done on other GPUs.

Serve with vLLM

Validated on DGX Spark with vllm/vllm-openai:nightly-aarch64:

vllm serve dmnsh/Ornith-1.0-9B-NVFP4 \
  --quantization modelopt_mixed \
  --max-model-len 4096 \
  --gpu-memory-utilization 0.164 \
  --served-model-name Ornith-1.0-9B-NVFP4

Notes:

Use --quantization modelopt_mixed for this mixed NVFP4+FP8 checkpoint.
For longer contexts, raise --max-model-len and --gpu-memory-utilization as needed.
Ornith is a reasoning model; enable a reasoning / tool parser when serving for agents (see the base model card).

DGX Spark speedups (BF16 → NVFP4)

vLLM on GB10, max-model-len=4096, concurrency 1.

Metric	BF16	NVFP4	Change
Memory (GiB)	30.25	25.66	−15%
Prefill TTFT (ms)	435.7	151.3	−65% (2.9× faster)
Throughput (tok/s)	12.2	28.8	+135% (2.35×)

Files to ignore in this local folder

If uploading from a local checkout that still has working artifacts, do not upload:

model.safetensors.pre_lmhead_fix
hf_quant_config.json.bak
.quant_summary.txt

Disclaimer

This checkpoint is provided as-is for experimentation. Quantization can change model quality; run your own evals before production use. Not affiliated with DeepReinforce or NVIDIA beyond use of open ModelOpt tooling.

Downloads last month: 17

Safetensors

Model size

7B params

Tensor type

BF16

F8_E4M3

Model tree for dmnsh/Ornith-1.0-9B-NVFP4

Base model

deepreinforce-ai/Ornith-1.0-9B

Quantized

(90)

this model