NVIDIA-Nemotron-Nano-12B-v2 GGUF size and VRAM requirements

⬇ 57,144 ❤ 2
Parameters12.31B
Context1,048,576

MaziyarPanahi/NVIDIA-Nemotron-Nano-12B-v2-GGUF is a large language model with 12.31 billion parameters, built on the nemotron_h architecture. It has been downloaded 57,144 times.

To run MaziyarPanahi/NVIDIA-Nemotron-Nano-12B-v2-GGUF locally at a 4,096-token context, its quantized versions need between 6.87 GB (Q2_K, lowest quality) and 25.43 GB (GGUF, highest quality) of memory, weights plus KV cache and a system margin included.

For most users the best balance is Q2_K, needing about 6.87 GB. That means MaziyarPanahi/NVIDIA-Nemotron-Nano-12B-v2-GGUF fits entirely in the VRAM of an 8 GB GPU or larger, running fully on the GPU.

→ Guide: How much VRAM do you need?

GGUF file size and memory by quantization

Compare real GGUF weight sizes, estimated KV cache and total memory for Q4, Q5, Q8 and every quantization published in this repository.

Quant.Bits QualityWeights KVTotal Speed~Verdict
Q2_K 3.06 Low 4.38 GB 1.69 GB 6.87 GB 91.3 t/s Fits in VRAM
Q3_K_M 3.91 Fair 5.61 GB 1.69 GB 8.1 GB 8.9 t/s Offload
Q3_K_L 4.14 Fair 5.94 GB 1.69 GB 8.43 GB 8.4 t/s Offload
Q4_K_M 4.87 Good 6.98 GB 1.69 GB 9.47 GB 7.2 t/s Offload
Q5_K_M 5.7 Very good 8.16 GB 1.69 GB 10.66 GB 6.1 t/s Offload
Q6_K 6.57 Excellent 9.42 GB 1.69 GB 11.91 GB 5.3 t/s Offload
GGUF 16.01 Excellent 22.94 GB 1.69 GB 25.43 GB Insufficient

KV cache estimated (architecture unavailable). Speed is a rough estimate bounded by memory bandwidth.

Frequently asked questions

How much VRAM do you need to run MaziyarPanahi/NVIDIA-Nemotron-Nano-12B-v2-GGUF?

You need about 6.87 GB of VRAM to run MaziyarPanahi/NVIDIA-Nemotron-Nano-12B-v2-GGUF entirely on the GPU using the Q2_K quantization (at a 4,096-token context). Smaller quantizations lower the requirement at the cost of quality.

Can I run MaziyarPanahi/NVIDIA-Nemotron-Nano-12B-v2-GGUF on an 8 GB GPU?

Yes. With 8 GB of VRAM you can run MaziyarPanahi/NVIDIA-Nemotron-Nano-12B-v2-GGUF fully on the GPU using Q2_K (about 6.87 GB).

Can I run MaziyarPanahi/NVIDIA-Nemotron-Nano-12B-v2-GGUF on a 16 GB GPU?

Yes. With 16 GB of VRAM you can run MaziyarPanahi/NVIDIA-Nemotron-Nano-12B-v2-GGUF fully on the GPU using Q6_K (about 11.91 GB).

Can I run MaziyarPanahi/NVIDIA-Nemotron-Nano-12B-v2-GGUF on a 24 GB GPU?

Yes. With 24 GB of VRAM you can run MaziyarPanahi/NVIDIA-Nemotron-Nano-12B-v2-GGUF fully on the GPU using Q6_K (about 11.91 GB).

What is the best quantization for MaziyarPanahi/NVIDIA-Nemotron-Nano-12B-v2-GGUF?

If memory allows, higher bits-per-weight means better quality. A common sweet spot is a Q4_K_M or Q5_K_M quantization, which keeps most of the quality while roughly halving the memory versus 8-bit. Pick the highest quantization that still fits in your VRAM.