LL

Llama-3.1-Nemotron-Nano-8B-V1

LlamaGGUF by unslothUpdated 2025-05-22
Download on Hugging Face
Parameters8B
Context128K
Layers32
Architecturellama
Smallest quant2.2 GB
Quick answer

Llama-3.1-Nemotron-Nano-8B-V1 needs about 6.5 GB of memory at Q4_K_M (a 4.9 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 25 quants, from 2.2 GB (IQ1_S) to 16.1 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

Llama‑3.1‑Nemotron‑Nano‑8B‑V1 – a compact 8B reasoning model

Llama‑3.1‑Nemotron‑Nano‑8B‑V1 is a dense decoder‑only transformer with 8B parameters. It is post‑trained for reasoning, chat, RAG, and tool calling. The model supports a context length of 128K and fits on a single RTX GPU.

Good at

  • Reasoning tasks
  • Chat and instruction following
  • RAG and tool calling

Limits

  • No vision support
  • Requires 8K context for memory estimates
  • License governed by NVIDIA Open Model License

Best for

  • Local chatbot deployment
  • AI agent development
  • RAG system integration

Who it’s for. Developers building AI agents, chatbots, or RAG systems who need a balance of accuracy and efficiency on a single RTX GPU. The model is ready for commercial use under the NVIDIA Open Model License.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S2.2 GB 3.7 GB
Fits Get file →
IQ1_M2.3 GB 3.9 GB
Fits Get file →
IQ2_XXS2.5 GB 4.1 GB
Fits Get file →
IQ2_M3.0 GB 4.6 GB
Fits Get file →
Q2_K3.2 GB 4.8 GB
Fits Get file →
Q2_K_L3.3 GB 4.9 GB
Fits Get file →
IQ3_XXS3.3 GB 4.9 GB
Fits Get file →
Q2_K_XL3.4 GB 5.0 GB
Fits Get file →
Q3_K_S3.7 GB 5.2 GB
Fits Get file →
Q3_K_M4.0 GB 5.6 GB
Fits Get file →
Q3_K_XL4.2 GB 5.8 GB
Fits Get file →
IQ4_XS4.5 GB 6.0 GB
Fits Get file →
Q4_04.7 GB 6.2 GB
Fits Get file →
IQ4_NL4.7 GB 6.3 GB
Fits Get file →
Q4_K_S4.7 GB 6.3 GB
Fits Get file →
Q4_K_M4.9 GB 6.5 GB
Fits Get file →
Q4_K_XL5.0 GB 6.6 GB
Fits Get file →
Q4_15.1 GB 6.7 GB
Fits Get file →
Q5_K_S5.6 GB 7.2 GB
Fits Get file →
Q5_K_M5.7 GB 7.3 GB
Tight Get file →
Q5_K_XL5.7 GB 7.3 GB
Tight Get file →
Q6_K6.6 GB 8.2 GB
Too big Get file →
Q6_K_XL7.3 GB 8.9 GB
Too big Get file →
Q8_K_XL10.6 GB 12.1 GB
Too big Get file →
BF1616.1 GB 17.6 GB
Too big Get file →

For 8 GB VRAM, use IQ1_S (file size 2.16 GB, memory 3.7 GB) or IQ1_M (2.29 GB, 3.9 GB). With 12 GB VRAM, Q4_K_XL (4.99 GB, 6.6 GB) or Q5_K_XL (5.74 GB, 7.3 GB) are suitable. Higher memory allows Q6_K_XL (7.33 GB, 8.9 GB).

What GPU do you need for Llama-3.1-Nemotron-Nano-8B-V1?

These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.

  • 4 GB VRAM: the best quant that fits is IQ1_M (2.3 GB file, about 3.9 GB in use).
  • 6 GB VRAM: the best quant that fits is IQ4_XS (4.5 GB file, about 6.0 GB in use).
  • 8 GB VRAM: the best quant that fits is Q5_K_XL (5.7 GB file, about 7.3 GB in use).
  • 12 GB VRAM: the best quant that fits is Q6_K_XL (7.3 GB file, about 8.9 GB in use).
  • 16 GB VRAM: the best quant that fits is Q8_K_XL (10.6 GB file, about 12.1 GB in use).
  • 24 GB VRAM: the best quant that fits is BF16 (16.1 GB file, about 17.6 GB in use).

Which Llama-3.1-Nemotron-Nano-8B-V1 quant should you choose?

Q4_K_M is the usual starting point for Llama-3.1-Nemotron-Nano-8B-V1: it balances file size and quality well. Here it is a 4.9 GB file.

If memory is tight, the smallest file is IQ1_S at 2.2 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters8B
Layers32
Trained context131,072 tokens
KV cache (fp16)128 KB per token

Source

Quantized byunsloth
FamilyLlama
Licenseother
Downloads (HF)3,528
Last updated2025-05-22

Frequently asked questions about Llama-3.1-Nemotron-Nano-8B-V1

How much VRAM does Llama-3.1-Nemotron-Nano-8B-V1 need?

About 6.5 GB at Q4_K_M with an 8K context window. That is the 4.9 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.

Can I run Llama-3.1-Nemotron-Nano-8B-V1 on an 8 GB GPU?

Yes, with Q5_K_XL: the 5.7 GB file needs about 7.3 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Llama-3.1-Nemotron-Nano-8B-V1 GGUF?

It depends on the quant: IQ1_S is 2.2 GB, IQ1_M is 2.3 GB, IQ2_XXS is 2.5 GB, IQ2_M is 3.0 GB, Q2_K is 3.2 GB, Q2_K_L is 3.3 GB and 19 more.

What context length does Llama-3.1-Nemotron-Nano-8B-V1 support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.3 GB at 32K.

Where can I download Llama-3.1-Nemotron-Nano-8B-V1 GGUF?

The files are on Hugging Face in the unsloth/Llama-3.1-Nemotron-Nano-8B-v1-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does Llama-3.1-Nemotron-Nano-8B-V1 use?

Hugging Face lists the license as other. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Can I run Llama‑3.1‑Nemotron‑Nano‑8B‑V1 on 8 GB VRAM?

Yes, use IQ1_S or IQ1_M quantizations; they require approximately 3.7–3.9 GB VRAM at 8K context.

Does the model support vision inputs?

No, the model has no vision capability.

What context length does the model support?

The model supports a context length of 128K tokens.

Other GGUFs of Llama-3.1-Nemotron-Nano-8B-v1

Similar models

Browse all →

More from unsloth

All by unsloth →

More Llama models

All Llama →

Other small models

All small models →