Instructions to use ukkathva/AdaptKey-Nemotron-30b-FP8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ukkathva/AdaptKey-Nemotron-30b-FP8 with Transformers:

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

pipe = pipeline("text-generation", model="ukkathva/AdaptKey-Nemotron-30b-FP8")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("ukkathva/AdaptKey-Nemotron-30b-FP8", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use ukkathva/AdaptKey-Nemotron-30b-FP8 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ukkathva/AdaptKey-Nemotron-30b-FP8"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ukkathva/AdaptKey-Nemotron-30b-FP8",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ukkathva/AdaptKey-Nemotron-30b-FP8

SGLang

How to use ukkathva/AdaptKey-Nemotron-30b-FP8 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 "ukkathva/AdaptKey-Nemotron-30b-FP8" \
    --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": "ukkathva/AdaptKey-Nemotron-30b-FP8",
		"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 "ukkathva/AdaptKey-Nemotron-30b-FP8" \
        --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": "ukkathva/AdaptKey-Nemotron-30b-FP8",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use ukkathva/AdaptKey-Nemotron-30b-FP8 with Docker Model Runner:
```
docker model run hf.co/ukkathva/AdaptKey-Nemotron-30b-FP8
```

Configuration Parsing Warning:Invalid JSON for config file config.json

AdaptKey-Nemotron-30b-FP8

FP8 Dynamic quantization of AdaptKey/AdaptKey-Nemotron-30b (hybrid Mamba2 + MoE).

Quantization

Scheme: FP8_DYNAMIC (W8A8, per-channel weights, dynamic per-token activations)
Serialization: compressed-tensors
Kept at higher precision: MoE routers (mixer.gate), Mamba2 state params (A_log, D, dt_bias, conv1d), all norms, embeddings, lm_head, the attention projections and the Mamba projections immediately preceding each attention block.

Serving with vLLM

config.json declares auto_map -> configuration_nemotron_h.NemotronHConfig and the file ships with the checkpoint, so --trust-remote-code is required for transformers to parse the config. vLLM then uses its own native NemotronHForCausalLM implementation for the weights.

vllm serve ukkathva/AdaptKey-Nemotron-30b-FP8 \
  --trust-remote-code \
  --tensor-parallel-size 1 \
  --max-model-len 131072 \
  --gpu-memory-utilization 0.90

On NVIDIA Ampere (A100, sm_80) there is no native FP8 tensor-core path; vLLM serves FP8 MoE via its MARLIN backend, so the benefit is memory, not throughput.

Downloads last month: 30

Safetensors

Model size

32B params

Tensor type

F32

BF16

F8_E4M3

Model tree for ukkathva/AdaptKey-Nemotron-30b-FP8

Base model

AdaptKey/AdaptKey-Nemotron-30b

Quantized

(1)

this model