Instructions to use chankhavu/Nemotron-Cascade-2-30B-A3B-FP8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use chankhavu/Nemotron-Cascade-2-30B-A3B-FP8 with Transformers:

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

pipe = pipeline("text-generation", model="chankhavu/Nemotron-Cascade-2-30B-A3B-FP8", 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("chankhavu/Nemotron-Cascade-2-30B-A3B-FP8", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("chankhavu/Nemotron-Cascade-2-30B-A3B-FP8", 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 Settings

vLLM

How to use chankhavu/Nemotron-Cascade-2-30B-A3B-FP8 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "chankhavu/Nemotron-Cascade-2-30B-A3B-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": "chankhavu/Nemotron-Cascade-2-30B-A3B-FP8",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/chankhavu/Nemotron-Cascade-2-30B-A3B-FP8

SGLang

How to use chankhavu/Nemotron-Cascade-2-30B-A3B-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 "chankhavu/Nemotron-Cascade-2-30B-A3B-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": "chankhavu/Nemotron-Cascade-2-30B-A3B-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 "chankhavu/Nemotron-Cascade-2-30B-A3B-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": "chankhavu/Nemotron-Cascade-2-30B-A3B-FP8",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use chankhavu/Nemotron-Cascade-2-30B-A3B-FP8 with Docker Model Runner:
```
docker model run hf.co/chankhavu/Nemotron-Cascade-2-30B-A3B-FP8
```

Nemotron-Cascade-2-30B-A3B-FP8

FP8 W8A8 quantization of Nemotron-Cascade-2-30B-A3B — a 32B hybrid Mamba-MoE reasoning model (3.2B active). Quantized with NVIDIA ModelOpt using the same selective quantization recipe as NVIDIA's official Nano FP8: MoE experts and Mamba GEMMs in FP8, attention and sensitive layers in BF16, KV cache in FP8.

Benchmarks

Calculated using NVIDIA-NeMo/Evaluator with config from Nemotron-3-Super-120B's eval config:

Benchmark	Nemotron-Cascade-2-30B-A3B (reproduced results)	Nemotron-Cascade-2-30B-A3B-FP8 (this model)
AIME 2025 (avg@8)	98.8	96.7
AIME 2026 (avg@8)	94.2	95.0
HMMT Feb 2025 (avg@8)	92.9	93.8

With the low sample count (8 rollouts per problem), a deviation of ±2% accross runs is expected. Safe to say BF16 and FP8 variants are equivalent in reasoning performance.

Quantization Details

Method: FP8 Post-Training Quantization (PTQ), without Quantization-Aware Distillation (QAD)
Format: FP8 E4M3 — static per-tensor weight scaling, dynamic per-token activation scaling at inference
KV cache: FP8
Tooling: NVIDIA ModelOpt

Selective Quantization Recipe

Follows the Nano-architecture selective quantization recipe from the Nemotron 3 Nano Technical Report (Section 4). Same recipe as NVIDIA's official FP8 checkpoint. Sensitive components are kept in higher precision:

Component	Precision	Rationale
MoE expert GEMMs (routed + shared)	FP8	All 23 MoE layers, 128 routed + 2 shared experts each
Mamba GEMMs (non-adjacent)	FP8	17 of 23 Mamba layers
Attention layers (all 6)	BF16	Most sensitive — kept BF16 per NVIDIA sensitivity analysis
Mamba layers adjacent to attention (6)	BF16	Layers {4, 11, 18, 25, 32, 41} — found sensitive in ablations
Mamba 1D conv	BF16	All layers
Router gates	FP32	Routing precision must not degrade
Embeddings & lm_head	BF16	Not quantized
KV cache	FP8	All 6 attention layers

Calibration

Dataset: 4,000 samples from nvidia/Nemotron-Cascade-2-SFT-Data
Domain mix: math (1000), swe (900), terminal_agent (500), science (500), chat (400), conversational_agent (300), instruction_following (300), safety (100)
Sequence length: Up to 12,288 tokens (no padding, natural length per sample)

Usage

SGLang

python -m sglang.launch_server \
    --model chankhavu/Nemotron-Cascade-2-30B-A3B-FP8 \
    --trust-remote-code \
    --tool-call-parser qwen3_coder \
    --reasoning-parser nano_v3

vLLM

vllm serve chankhavu/Nemotron-Cascade-2-30B-A3B-FP8 \
    --mamba_ssm_cache_dtype float32 \
    --max-model-len 262144 \
    --trust-remote-code \
    --enable-auto-tool-choice \
    --tool-call-parser qwen3_coder \
    --reasoning-parser nemotron_v3

Acknowledgments

Quantization recipe based on the Nemotron 3 Nano Technical Report
Quantized with NVIDIA ModelOpt

Downloads last month: 1,538

Safetensors

Model size

32B params

Tensor type

F32

BF16

F8_E4M3

Model tree for chankhavu/Nemotron-Cascade-2-30B-A3B-FP8

Base model

nvidia/Nemotron-Cascade-2-30B-A3B

Quantized

(30)

this model

chankhavu
/

Nemotron-Cascade-2-30B-A3B-FP8

Nemotron-Cascade-2-30B-A3B-FP8

Benchmarks

Quantization Details

Selective Quantization Recipe

Calibration

Usage

SGLang

vLLM

Acknowledgments

Model tree for chankhavu/Nemotron-Cascade-2-30B-A3B-FP8

Dataset used to train chankhavu/Nemotron-Cascade-2-30B-A3B-FP8