Nemotron 3 Nano 30B A3B GGUF — Hardware Requirements & GPU Compatibility
Chat
This is a GGUF-quantized version of NVIDIA's Nemotron 3 Nano 30B A3B, repackaged by Unsloth. Nemotron 3 Nano is NVIDIA's efficient language model using a Mixture-of-Experts (MoE) architecture with 30 billion total parameters and approximately 3 billion active parameters per token, designed to deliver strong performance with minimal computational overhead. The sparse MoE design makes this model far more efficient than its total parameter count suggests, requiring VRAM closer to a dense 3B model while producing output quality that competes with much larger architectures. Unsloth's GGUF conversion enables compatibility with llama.cpp and popular local inference frontends, making it an appealing option for users who want high-quality local inference without the hardware demands of a full 30B dense model.
116.9K downloads
277 likesSpecifications
- Publisher
- Unsloth
- Parameters
- 30B
- Release Date
- 2025-12-31
- License
- Other
Get Started
HuggingFace
How Much VRAM Does Nemotron 3 Nano 30B A3B GGUF Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| IQ2_XXS | 2.20 | 9.1 GB | — | 8.25 GB | Importance-weighted 2-bit, extreme compression — significant quality loss |
| IQ2_M | 2.70 | 11.1 GB | — | 10.13 GB | Importance-weighted 2-bit, medium |
| IQ3_XXS | 3.10 | 12.8 GB | — | 11.63 GB | Importance-weighted 3-bit |
| Q2_K | 3.40 | 14.0 GB | — | 12.75 GB | 2-bit quantization with K-quant improvements |
| Q3_K_S | 3.50 | 14.4 GB | — | 13.13 GB | 3-bit small quantization |
| Q3_K_M | 3.90 | 16.1 GB | — | 14.63 GB | 3-bit medium quantization |
| Q4_0 | 4.00 | 16.5 GB | — | 15.00 GB | 4-bit legacy quantization |
| IQ4_XS | 4.30 | 17.7 GB | — | 16.13 GB | Importance-weighted 4-bit, compact |
| Q4_1 | 4.50 | 18.6 GB | — | 16.88 GB | 4-bit legacy quantization with offset |
| Q4_K_S | 4.50 | 18.6 GB | — | 16.88 GB | 4-bit small quantization |
| IQ4_NL | 4.50 | 18.6 GB | — | 16.88 GB | Importance-weighted 4-bit, non-linear |
| Q4_K_M | 4.80 | 19.8 GB | — | 18.00 GB | 4-bit medium quantization — most popular sweet spot |
| Q5_K_S | 5.50 | 22.7 GB | — | 20.63 GB | 5-bit small quantization |
| Q5_K_M | 5.70 | 23.5 GB | — | 21.38 GB | 5-bit medium quantization — good quality/size tradeoff |
| Q6_K | 6.60 | 27.2 GB | — | 24.75 GB | 6-bit quantization, very good quality |
| Q8_0 | 8.00 | 33 GB | — | 30.00 GB | 8-bit quantization, near-lossless |
Which GPUs Can Run Nemotron 3 Nano 30B A3B GGUF?
Q4_K_M · 19.8 GBNemotron 3 Nano 30B A3B GGUF (Q4_K_M) requires 19.8 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 26+ GB is recommended. 6 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti.
Runs great
— Plenty of headroom
Which Devices Can Run Nemotron 3 Nano 30B A3B GGUF?
Q4_K_M · 19.8 GB21 devices with unified memory can run Nemotron 3 Nano 30B A3B GGUF, including NVIDIA DGX H100, NVIDIA DGX A100 640GB, Mac Mini M4 Pro (24 GB).
Runs great
— Plenty of headroomRelated Models
Frequently Asked Questions
- How much VRAM does Nemotron 3 Nano 30B A3B GGUF need?
Nemotron 3 Nano 30B A3B GGUF requires 19.8 GB of VRAM at Q4_K_M, or 33 GB at Q8_0.
VRAM = Weights + KV Cache + Overhead
Weights = 30B × 4.8 bits ÷ 8 = 18 GB
KV Cache + Overhead ≈ 1.8 GB (at 2K context + ~0.3 GB framework)
VRAM usage by quantization
Q4_K_M19.8 GB- Can NVIDIA GeForce RTX 4090 run Nemotron 3 Nano 30B A3B GGUF?
Yes, at Q5_K_M (23.5 GB) or lower. Higher quantizations like Q6_K (27.2 GB) exceed the NVIDIA GeForce RTX 4090's 24 GB.
- What's the best quantization for Nemotron 3 Nano 30B A3B GGUF?
For Nemotron 3 Nano 30B A3B GGUF, Q4_K_M (19.8 GB) offers the best balance of quality and VRAM usage. Q5_K_S (22.7 GB) provides better quality if you have the VRAM. The smallest option is IQ2_XXS at 9.1 GB.
VRAM requirement by quantization
IQ2_XXS9.1 GB~53%Q3_K_S14.4 GB~77%Q4_118.6 GB~88%Q4_K_M ★19.8 GB~89%Q5_K_S22.7 GB~92%Q8_033.0 GB~99%★ Recommended — best balance of quality and VRAM usage.
- Can I run Nemotron 3 Nano 30B A3B GGUF on a Mac?
Nemotron 3 Nano 30B A3B GGUF requires at least 9.1 GB at IQ2_XXS, 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 Nemotron 3 Nano 30B A3B GGUF locally?
Yes — Nemotron 3 Nano 30B A3B GGUF can run locally on consumer hardware. At Q4_K_M quantization it needs 19.8 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.
- How fast is Nemotron 3 Nano 30B A3B GGUF?
At Q4_K_M, Nemotron 3 Nano 30B A3B GGUF can reach ~147 tok/s on AMD Instinct MI300X. On NVIDIA GeForce RTX 4090: ~33 tok/s. 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 ÷ 19.8 × 0.55 = ~147 tok/s
Estimated speed at Q4_K_M (19.8 GB)
AMD Instinct MI300X~147 tok/sNVIDIA GeForce RTX 4090~33 tok/sNVIDIA H100 SXM~110 tok/sAMD Instinct MI250X~91 tok/sReal-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
- What's the download size of Nemotron 3 Nano 30B A3B GGUF?
At Q4_K_M, the download is about 18.00 GB. The full-precision Q8_0 version is 30.00 GB. The smallest option (IQ2_XXS) is 8.25 GB.