Instructions to use julianmb/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-ROCmFP4-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use julianmb/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-ROCmFP4-GGUF with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf julianmb/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-ROCmFP4-GGUF
# Run inference directly in the terminal:
llama cli -hf julianmb/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-ROCmFP4-GGUF

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf julianmb/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-ROCmFP4-GGUF
# Run inference directly in the terminal:
llama cli -hf julianmb/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-ROCmFP4-GGUF

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf julianmb/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-ROCmFP4-GGUF
# Run inference directly in the terminal:
./llama-cli -hf julianmb/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-ROCmFP4-GGUF

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf julianmb/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-ROCmFP4-GGUF
# Run inference directly in the terminal:
./build/bin/llama-cli -hf julianmb/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-ROCmFP4-GGUF

Use Docker

docker model run hf.co/julianmb/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-ROCmFP4-GGUF

LM Studio
Jan

vLLM

How to use julianmb/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-ROCmFP4-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "julianmb/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-ROCmFP4-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "julianmb/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-ROCmFP4-GGUF",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/julianmb/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-ROCmFP4-GGUF

Ollama
How to use julianmb/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-ROCmFP4-GGUF with Ollama:
```
ollama run hf.co/julianmb/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-ROCmFP4-GGUF
```
Unsloth Desktop
Docker Model Runner
How to use julianmb/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-ROCmFP4-GGUF with Docker Model Runner:
```
docker model run hf.co/julianmb/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-ROCmFP4-GGUF
```

Lemonade

How to use julianmb/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-ROCmFP4-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull julianmb/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-ROCmFP4-GGUF

Run and chat with the model

lemonade run user.NVIDIA-Nemotron-3.5-Lightning-30B-A3B-ROCmFP4-GGUF-{{QUANT_TAG}}

List all available models

lemonade list

Atomic Chat

NVIDIA Nemotron 3.5 Lightning 30B-A3B — ROCmFP4 GGUF

Quantized GGUF conversions of NVIDIA Nemotron 3.5 Lightning 30B-A3B Base (BF16) using the experimental ROCmFPX quantization family from the ROCmFPX llama.cpp fork.

IMPORTANT: These files use custom Q4_0_ROCMFP4_* GGUF tensor types. They are not loadable by mainline llama.cpp. You must build/run the ROCmFPX fork (see how_to_use.md). They are tuned and validated on AMD Strix Halo / RDNA3.5 (gfx1151), with HIP/ROCm and Vulkan kernel support (plus CPU reference paths).

Note on Hugging Face Hub metadata: The Hub warning "We're not able to determine the quantization variants" is expected because Q4_0_ROCMFP4_* are experimental, non-standard GGUF types. The table below is authoritative.

Files

File	Preset	bpw	Size	Notes
`NVIDIA-Nemotron-3.5-Lightning-30B-A3B-ROCmFP4-STRIX_LEAN.gguf`	`Q4_0_ROCMFP4_STRIX_LEAN`	~4.38	15.73 GiB	Recommended. Strix Halo K/V recipe + Q5_K token embeddings
`NVIDIA-Nemotron-3.5-Lightning-30B-A3B-ROCmFP4-FAST.gguf`	`Q4_0_ROCMFP4_FAST`	~4.25	15.66 GiB	Speed-first single-scale layout
`NVIDIA-Nemotron-3.5-Lightning-30B-A3B-ROCmFP4-COHERENT.gguf`	`Q4_0_ROCMFP4_COHERENT`	~4.70	16.74 GiB	Agent/tool/JSON/code preset (protected embeddings + Q8_0)

All files are quantized from the BF16 source (recommended quality path) and advertise context_length = 262144 (the model's real max_position_embeddings).

Note: Token embeddings for 2688 hidden dimensions fall back from Q5_K/Q6_K to Q5_1/Q8_0 because 2688 is not divisible by 256.

Model overview

Architecture: nemotron_h_moe (hybrid Mamba2 / Attention / MoE)
52 layers: 23 Mamba2 + 6 Attention + 23 MoE
128 routed experts, 6 active (A3B), 1 shared expert
~31.6B total params (3.5B active per token, A3B)
Vocabulary: 131072 · Context: 262144 (256K)
License: OpenMDW-1.1 (see LICENSE)

Quality & Benchmarks

Preset	Vulkan0 Prompt (pp512)	Vulkan0 Decode (tg128)	ROCm0 Prompt (pp512)	ROCm0 Decode (tg128)
`FAST` (`Q4_0_ROCMFP4_FAST`)	1310.5 t/s	86.0 t/s	1079.3 t/s	80.3 t/s
`STRIX_LEAN` (`Q4_0_ROCMFP4_STRIX_LEAN`)	1299.7 t/s	85.6 t/s	1075.4 t/s	79.4 t/s
`COHERENT` (`Q4_0_ROCMFP4_COHERENT`)	1290.4 t/s	81.6 t/s	1302.2 t/s	77.8 t/s

Perplexity: STRIX_LEAN scores 5.9936 ± 0.0358 on wikitext-2. Measured on Framework AMD Strix Halo (128 GB unified RAM, gfx1151, ROCm 7.2.3).

Speculative decoding (embedded MTP)

This model carries an MTP head that works well on its hybrid MoE architecture (unlike some other hybrids). Measured on Strix Halo with the tuned profile (draft-n 6 / p-min 0.60):

Path	Decode
Bare (STRIX_LEAN)	52.4 tok/s
+ embedded MTP	🔥 84.5 – 95.2 tok/s

Draft acceptance ≈ 88%. Serve via halofpx (halofpx load nemotron-3.5-30b applies this profile automatically).

Quick start

See how_to_use.md for full instructions (build + run).

# 1. Build the ROCmFPX fork
git clone https://github.com/charlie12345/ROCmFPX.git
cd ROCmFPX && env JOBS=16 scripts/build-strix-rocmfp4-mtp.sh   # Strix Halo

# 2. Run on Vulkan (recommended on Strix Halo)
build-strix-rocmfp4/bin/llama-completion -m NVIDIA-Nemotron-3.5-Lightning-30B-A3B-ROCmFP4-STRIX_LEAN.gguf \
  -p "What is 2+2?" -n 64 -dev Vulkan0 -ngl 999 -fa on -c 8192

# 3. Or on HIP/ROCm (unified memory enables APUs/iGPUs)
HSA_OVERRIDE_GFX_VERSION=11.5.1 GGML_HIP_ENABLE_UNIFIED_MEMORY=1 \
  build-strix-rocmfp4/bin/llama-completion -m NVIDIA-Nemotron-3.5-Lightning-30B-A3B-ROCmFP4-STRIX_LEAN.gguf \
  -p "What is 2+2?" -n 64 -dev ROCm0 -ngl 999 -fa on -c 8192

Technical Notes & Findings

MTP/NextN head is not included in this conversion (the NemotronH converter skips mtp.* tensors for MoE models).
NVFP4 path analysis: We evaluated converting the native NVFP4 checkpoint. With our converter patches, native NVFP4 GGUF loads, but scores PPL 109.79 because runtime kernels do not integrate ModelOpt's companion scale2 factor (~1.4e-4). The clean BF16 → ROCmFP4 path is used for all delivered models.
Converter patches, reproduction scripts, and full benchmark notes are available in the companion repo: julianmb/nemotron-3.5-30b-a3b-rocmfp4 on GitHub.

Credits

Model: NVIDIA (weights, architecture, license: OpenMDW-1.1)
ROCmFPX / ROCmFP4 quantization + kernels: charlie12345/ROCmFPX
Conversion & quantization performed by: julianmb

Downloads last month: 366

GGUF

Model size

32B params

Architecture

nemotron_h_moe

Hardware compatibility

We're not able to determine the quantization variants.

View all variants

Model tree for julianmb/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-ROCmFP4-GGUF

Base model

nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-Base-BF16

Quantized

(3)

this model