LL

llama2 70b longlora 32k ROPE8

LlamaGGUF by grimulkanUpdated 2024-01-31
Download on Hugging Face
Parameters69B
Context4K
Layers80
Architecturellama
Smallest quant29.9 GB
Quick answer

llama2 70b longlora 32k ROPE8 needs about 33.1 GB of memory at Q3_K_S (a 29.9 GB file) with an 8K context window, so it fits on a 48 GB GPU.

llama2 70b longlora 32k ROPE8 is a 69B-parameter Llama model in GGUF format, quantized by grimulkan. Its trained context length is 4K tokens. The repository has 1 quant file, from 29.9 GB (Q3_K_S) to 29.9 GB (Q3_K_S).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q3_K_S29.9 GB 31.8 GB
Too big Get file →

What GPU do you need for llama2 70b longlora 32k ROPE8?

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: the best quant that fits is Q3_K_S (29.9 GB file, about 33.1 GB in use).

Which llama2 70b longlora 32k ROPE8 quant should you choose?

Q3_K_S (29.9 GB) is the middle option in this repository. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters69B
Layers80
Trained context4,096 tokens
KV cache (fp16)320 KB per token

Source

Quantized bygrimulkan
FamilyLlama
Licensellama2
Downloads (HF)22
Last updated2024-01-31

Frequently asked questions about llama2 70b longlora 32k ROPE8

How much VRAM does llama2 70b longlora 32k ROPE8 need?

About 33.1 GB at Q3_K_S with an 8K context window. That is the 29.9 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 llama2 70b longlora 32k ROPE8 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 33.1 GB, so you would need a larger GPU or CPU offloading.

What is the file size of llama2 70b longlora 32k ROPE8 GGUF?

It depends on the quant: Q3_K_S is 29.9 GB.

What context length does llama2 70b longlora 32k ROPE8 support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 2.7 GB at 8K and 1.3 GB at 4K.

Where can I download llama2 70b longlora 32k ROPE8 GGUF?

The files are on Hugging Face in the grimulkan/llama2_70b_longlora_32k_ROPE8_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 llama2 70b longlora 32k ROPE8 use?

Hugging Face lists the license as llama2. 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 grimulkan

All by grimulkan →

More Llama models

All Llama →

Other large models

All large models →