LL

Reflection 70b PreciseQuant 6bpw

LlamaGGUF by nistenUpdated 2024-09-07
Download on Hugging Face
Parameters70.6B
Context8K
Layers80
Architecturellama
Smallest quant53.5 GB
Quick answer

Reflection 70b PreciseQuant 6bpw needs about 56.6 GB of memory at its main file (a 53.5 GB file) with an 8K context window, which is more than a 48 GB GPU holds.

Reflection 70b PreciseQuant 6bpw is a 70.6B-parameter Llama model in GGUF format, quantized by nisten. Its trained context length is 8K tokens. The repository has 1 quant file, from 53.5 GB to 53.5 GB.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—53.5 GB (2 parts) 56.6 GB
Too big Get file →

What GPU do you need for Reflection 70b PreciseQuant 6bpw?

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.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters70.6B
Layers80
Trained context8,192 tokens
KV cache (fp16)320 KB per token

Source

Quantized bynisten
FamilyLlama
Licensellama3.1
Downloads (HF)14
Last updated2024-09-07

Frequently asked questions about Reflection 70b PreciseQuant 6bpw

How much VRAM does Reflection 70b PreciseQuant 6bpw need?

About 56.6 GB at its main file with an 8K context window. That is the 53.5 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 Reflection 70b PreciseQuant 6bpw on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 56.6 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Reflection 70b PreciseQuant 6bpw GGUF?

It depends on the quant: file is 53.5 GB.

What context length does Reflection 70b PreciseQuant 6bpw support?

The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 2.7 GB at 8K and 2.7 GB at 8K.

Where can I download Reflection 70b PreciseQuant 6bpw GGUF?

The files are on Hugging Face in the nisten/Reflection-70b-PreciseQuant-6bpw-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 Reflection 70b PreciseQuant 6bpw 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.

Other GGUFs of Reflection-Llama-3.1-70B

Similar models

Browse all →

More from nisten

All by nisten →

More Llama models

All Llama →

Other large models

All large models →