LL

openbuddy codellama2 34b v11.1

LlamaGGUF by LeeEricUpdated 2023-09-29
Download on Hugging Face
Parameters33.8B
Context16K
Layers48
Architecturellama
Smallest quant20.3 GB
Quick answer

openbuddy codellama2 34b v11.1 needs about 22.4 GB of memory at Q4_K_M (a 20.3 GB file) with an 8K context window, so it fits on a 24 GB GPU.

openbuddy codellama2 34b v11.1 is a 33.8B-parameter Llama model in GGUF format, quantized by LeeEric. Its trained context length is 16K tokens. The repository has 1 quant file, from 20.3 GB (Q4_K_M) to 20.3 GB (Q4_K_M).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M20.3 GB 22.4 GB
Too big Get file →

What GPU do you need for openbuddy codellama2 34b v11.1?

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 Q4_K_M (20.3 GB file, about 22.4 GB in use).

Which openbuddy codellama2 34b v11.1 quant should you choose?

Q4_K_M is the usual starting point for openbuddy codellama2 34b v11.1: it balances file size and quality well. Here it is a 20.3 GB file.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters33.8B
Layers48
Trained context16,384 tokens
KV cache (fp16)192 KB per token

Source

Quantized byLeeEric
FamilyLlama
Licensellama2
Downloads (HF)102
Last updated2023-09-29

Frequently asked questions about openbuddy codellama2 34b v11.1

How much VRAM does openbuddy codellama2 34b v11.1 need?

About 22.4 GB at Q4_K_M with an 8K context window. That is the 20.3 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 openbuddy codellama2 34b v11.1 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 22.4 GB, so you would need a larger GPU or CPU offloading.

What is the file size of openbuddy codellama2 34b v11.1 GGUF?

It depends on the quant: Q4_K_M is 20.3 GB.

What context length does openbuddy codellama2 34b v11.1 support?

The GGUF header lists a trained context length of 16,384 tokens (16K). The KV cache grows with the context you use: about 1.6 GB at 8K and 3.2 GB at 16K.

Where can I download openbuddy codellama2 34b v11.1 GGUF?

The files are on Hugging Face in the LeeEric/openbuddy-codellama2-34b-v11.1-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 openbuddy codellama2 34b v11.1 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 Llama models

All Llama →

Other medium models

All medium models →