LL

nvidia Llama 3.1 Nemotron 70B Instruct bf16 iMat CQ

LlamaGGUF by NexesQuantsUpdated 2025-01-19
Download on Hugging Face
Parameters70.6B
Context128K
Layers80
Architecturellama
Smallest quant48.1 GB
Quick answer

nvidia Llama 3.1 Nemotron 70B Instruct bf16 iMat CQ needs about 51.3 GB of memory at BF16 (a 48.1 GB file) with an 8K context window, which is more than a 48 GB GPU holds. Longer context needs more: at 32K tokens the KV cache alone adds about 10.7 GB.

nvidia Llama 3.1 Nemotron 70B Instruct bf16 iMat CQ is a 70.6B-parameter Llama model in GGUF format, quantized by NexesQuants. Its trained context length is 128K tokens. The repository has 1 quant file, from 48.1 GB (BF16) to 48.1 GB (BF16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
BF1648.1 GB 51.3 GB
Too big Get file →

What GPU do you need for nvidia Llama 3.1 Nemotron 70B Instruct bf16 iMat CQ?

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: no quant fits at an 8K context.
  • 6 GB VRAM: no quant fits at an 8K context.
  • 8 GB VRAM: no quant fits at an 8K context.
  • 12 GB VRAM: no quant fits at an 8K context.
  • 16 GB VRAM: no quant fits at an 8K context.
  • 24 GB VRAM: no quant fits at an 8K context.
  • 32 GB VRAM: no quant fits at an 8K context.
  • 48 GB VRAM: no quant fits at an 8K context.

Which nvidia Llama 3.1 Nemotron 70B Instruct bf16 iMat CQ quant should you choose?

BF16 (48.1 GB) is the middle option in this repository. The unquantized model. It gives original quality and needs the most memory, so it is mainly for conversion or reference.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters70.6B
Layers80
Trained context131,072 tokens
KV cache (fp16)320 KB per token

Source

Quantized byNexesQuants
FamilyLlama
Licensellama3.1
Downloads (HF)37
Last updated2025-01-19

Frequently asked questions about nvidia Llama 3.1 Nemotron 70B Instruct bf16 iMat CQ

How much VRAM does nvidia Llama 3.1 Nemotron 70B Instruct bf16 iMat CQ need?

About 51.3 GB at BF16 with an 8K context window. That is the 48.1 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 nvidia Llama 3.1 Nemotron 70B Instruct bf16 iMat CQ on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 51.3 GB, so you would need a larger GPU or CPU offloading.

What is the file size of nvidia Llama 3.1 Nemotron 70B Instruct bf16 iMat CQ GGUF?

It depends on the quant: BF16 is 48.1 GB.

What context length does nvidia Llama 3.1 Nemotron 70B Instruct bf16 iMat CQ support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 2.7 GB at 8K and 10.7 GB at 32K.

Where can I download nvidia Llama 3.1 Nemotron 70B Instruct bf16 iMat CQ GGUF?

The files are on Hugging Face in the NexesQuants/nvidia_Llama-3.1-Nemotron-70B-Instruct-bf16-iMat-CQ-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 nvidia Llama 3.1 Nemotron 70B Instruct bf16 iMat CQ use?

Hugging Face lists the license as llama3.1. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Similar models

Browse all →

More from NexesQuants

All by NexesQuants →

More Llama models

All Llama →

Other large models

All large models →