LL

Llama 3.1 WhiteRabbitNeo 2 70B

LlamaGGUF by bartowskiUpdated 2024-10-05
Download on Hugging Face
Parameters70.6B
Context128K
Layers80
Architecturellama
Smallest quant16.8 GB
Quick answer

Llama 3.1 WhiteRabbitNeo 2 70B needs about 45.7 GB of memory at Q4_K_M (a 42.5 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 18 quants, from 16.8 GB (IQ1_M) to 75.0 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 10.7 GB.

Llama 3.1 WhiteRabbitNeo 2 70B – a large language model with 70.6B parameters

Llama 3.1 WhiteRabbitNeo 2 70B is a 70.6B‑parameter model based on the Llama architecture. It supports a context length of 131072 tokens and is released under the llama3.1 license. The model is available in multiple GGUF quantizations.

Good at

  • Large context handling
  • High‑capacity reasoning
  • Extensive token coverage

Limits

  • No vision support
  • Requires large VRAM for full precision
  • License restricts commercial use

Best for

  • Research on long‑form text generation
  • Enterprise knowledge bases
  • Complex dialogue systems

Who it’s for. Developers and researchers needing a high‑capacity language model for text‑only applications. The model is suitable for environments with sufficient GPU memory and compliance with the llama3.1 license.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_M16.8 GB 19.9 GB
Too big Get file →
IQ2_XXS19.1 GB 22.3 GB
Too big Get file →
IQ2_XS21.1 GB 24.3 GB
Too big Get file →
IQ2_M24.1 GB 27.3 GB
Too big Get file →
Q2_K26.4 GB 29.6 GB
Too big Get file →
Q2_K_L27.4 GB 30.6 GB
Too big Get file →
IQ3_XXS27.5 GB 30.7 GB
Too big Get file →
Q3_K_S30.9 GB 34.1 GB
Too big Get file →
IQ3_M31.9 GB 35.1 GB
Too big Get file →
Q3_K_M34.3 GB 37.5 GB
Too big Get file →
Q3_K_L37.1 GB 40.3 GB
Too big Get file →
IQ4_XS37.9 GB 41.1 GB
Too big Get file →
Q3_K_XL38.1 GB 41.2 GB
Too big Get file →
Q4_040.1 GB 43.3 GB
Too big Get file →
Q4_K_M42.5 GB 45.7 GB
Too big Get file →
Q5_K_M49.9 GB (2 parts) 53.1 GB
Too big Get file →
Q6_K57.9 GB (2 parts) 61.1 GB
Too big Get file →
Q8_075.0 GB (2 parts) 78.2 GB
Too big Get file →

For 8 GB VRAM, use IQ1_M (file size 16.75 GB, memory 19.9 GB). For 12 GB VRAM, IQ2_XXS (19.1 GB, 22.3 GB). For 16 GB VRAM, IQ2_XS (21.14 GB, 24.3 GB). Higher VRAM allows larger quants such as Q4_K_M (42.52 GB, 45.7 GB).

What GPU do you need for Llama 3.1 WhiteRabbitNeo 2 70B?

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: the best quant that fits is IQ2_XXS (19.1 GB file, about 22.3 GB in use).
  • 32 GB VRAM: the best quant that fits is IQ3_XXS (27.5 GB file, about 30.7 GB in use).
  • 48 GB VRAM: the best quant that fits is Q4_K_M (42.5 GB file, about 45.7 GB in use).

Which Llama 3.1 WhiteRabbitNeo 2 70B quant should you choose?

Q4_K_M is the usual starting point for Llama 3.1 WhiteRabbitNeo 2 70B: it balances file size and quality well. Here it is a 42.5 GB file.

The Q8_0 file is 75.0 GB, about 1.8 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.

If memory is tight, the smallest file is IQ1_M at 16.8 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
Parameters70.6B
Layers80
Trained context131,072 tokens
KV cache (fp16)320 KB per token

Source

Quantized bybartowski
FamilyLlama
Licensellama3.1
Downloads (HF)2,805
Last updated2024-10-05

Frequently asked questions about Llama 3.1 WhiteRabbitNeo 2 70B

How much VRAM does Llama 3.1 WhiteRabbitNeo 2 70B need?

About 45.7 GB at Q4_K_M with an 8K context window. That is the 42.5 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 WhiteRabbitNeo 2 70B on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 19.9 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Llama 3.1 WhiteRabbitNeo 2 70B GGUF?

It depends on the quant: IQ1_M is 16.8 GB, IQ2_XXS is 19.1 GB, IQ2_XS is 21.1 GB, IQ2_M is 24.1 GB, Q2_K is 26.4 GB, Q2_K_L is 27.4 GB and 12 more.

What context length does Llama 3.1 WhiteRabbitNeo 2 70B 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 Llama 3.1 WhiteRabbitNeo 2 70B GGUF?

The files are on Hugging Face in the bartowski/Llama-3.1-WhiteRabbitNeo-2-70B-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 WhiteRabbitNeo 2 70B 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.

Can I run this model on 8 GB VRAM?

Use the IQ1_M quant. It requires approximately 19.9 GB of VRAM at 8k context, so 8 GB VRAM is insufficient.

Does this model support image input?

No, the model has no vision capabilities.

What license applies to this model?

The model is released under the llama3.1 license, which includes usage restrictions and indemnification clauses.

Other GGUFs of Llama-3.1-WhiteRabbitNeo-2-70B

Similar models

Browse all →

More from bartowski

All by bartowski →

More Llama models

All Llama →

Other large models

All large models →