NVIDIA Nemotron 3 Nano 30B A3B NVFP4 — Hardware Requirements & GPU Compatibility
Chat
NVIDIA Nemotron 3 Nano 30B A3B NVFP4 is the most aggressively quantized version of the Nemotron 3 Nano 30B, using NVIDIA's proprietary NVFP4 format to bring the effective size down to around 18.2 billion parameters worth of memory. This makes it accessible on GPUs that couldn't touch the BF16 or FP8 variants. NVFP4 is NVIDIA's custom 4-bit floating point quantization, optimized for their GPU architectures to minimize quality loss at extreme compression. If you're running a mid-range NVIDIA card and want MoE-level intelligence, this is the variant to try.
430.8K downloads
113 likesSpecifications
- Publisher
- NVIDIA
- Parameters
- 18.2B
- Architecture
- NemotronHForCausalLM
- Context Length
- 262,144 tokens
- Vocabulary Size
- 131,072
- Release Date
- 2026-03-15
- License
- Other
Get Started
HuggingFace
How Much VRAM Does NVIDIA Nemotron 3 Nano 30B A3B NVFP4 Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| BF16 | 16.00 | 36.9 GB | 45.9 GB | 36.48 GB | Brain floating point 16 — preferred for training |
Which GPUs Can Run NVIDIA Nemotron 3 Nano 30B A3B NVFP4?
BF16 · 36.9 GBNVIDIA Nemotron 3 Nano 30B A3B NVFP4 (BF16) requires 36.9 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 48+ GB is recommended. Using the full 262K context window can add up to 9.1 GB, bringing total usage to 45.9 GB. No single GPU has enough memory — multi-GPU or cluster setups are needed.
Which Devices Can Run NVIDIA Nemotron 3 Nano 30B A3B NVFP4?
BF16 · 36.9 GB11 devices with unified memory can run NVIDIA Nemotron 3 Nano 30B A3B NVFP4, including NVIDIA DGX H100, NVIDIA DGX A100 640GB, MacBook Pro 16" M4 Max (48 GB).
Runs great
— Plenty of headroom
Decent
— Enough memory, may be tightRelated Models
Frequently Asked Questions
- How much VRAM does NVIDIA Nemotron 3 Nano 30B A3B NVFP4 need?
NVIDIA Nemotron 3 Nano 30B A3B NVFP4 requires 36.9 GB of VRAM at BF16. Full 262K context adds up to 9.1 GB (45.9 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 18.2B × 16 bits ÷ 8 = 36.5 GB
KV Cache + Overhead ≈ 0.4 GB (at 2K context + ~0.3 GB framework)
KV Cache + Overhead ≈ 9.4 GB (at full 262K context)
VRAM usage by quantization
BF1636.9 GBBF16 + full context45.9 GB- Can NVIDIA GeForce RTX 5090 run NVIDIA Nemotron 3 Nano 30B A3B NVFP4?
No — NVIDIA Nemotron 3 Nano 30B A3B NVFP4 requires at least 36.9 GB at BF16, which exceeds the NVIDIA GeForce RTX 5090's 32 GB of VRAM.
- Can I run NVIDIA Nemotron 3 Nano 30B A3B NVFP4 on a Mac?
NVIDIA Nemotron 3 Nano 30B A3B NVFP4 requires at least 36.9 GB at BF16, which exceeds the unified memory of most consumer Macs. You would need a Mac Studio or Mac Pro with a high-memory configuration.
- Can I run NVIDIA Nemotron 3 Nano 30B A3B NVFP4 locally?
Yes — NVIDIA Nemotron 3 Nano 30B A3B NVFP4 can run locally on consumer hardware. At BF16 quantization it needs 36.9 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.
- How fast is NVIDIA Nemotron 3 Nano 30B A3B NVFP4?
At BF16, NVIDIA Nemotron 3 Nano 30B A3B NVFP4 can reach ~79 tok/s on AMD Instinct MI300X. Speed depends mainly on GPU memory bandwidth. Real-world results typically within ±20%.
tok/s = (bandwidth GB/s ÷ model GB) × efficiency
Example: AMD Instinct MI300X → 5300 ÷ 36.9 × 0.55 = ~79 tok/s
Estimated speed at BF16 (36.9 GB)
AMD Instinct MI300X~79 tok/sNVIDIA H100 SXM~59 tok/sAMD Instinct MI250X~49 tok/sReal-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
- What's the download size of NVIDIA Nemotron 3 Nano 30B A3B NVFP4?
At BF16, the download is about 36.48 GB.