EU

L3.3 70B Euryale v2.3 GGUF ooba

EuryaleGGUF by HuzderuUpdated 2024-12-10
Download on Hugging Face
Parameters70.6B
Context128K
Layers80
Architecturellama
Smallest quant57.9 GB
Quick answer

L3.3 70B Euryale v2.3 GGUF ooba needs about 61.1 GB of memory at Q6_K (a 57.9 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.

L3.3 70B Euryale v2.3 GGUF ooba is a 70.6B-parameter Euryale model in GGUF format, quantized by Huzderu. Its trained context length is 128K tokens. The repository has 1 quant file, from 57.9 GB (Q6_K) to 57.9 GB (Q6_K).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q6_K57.9 GB (2 parts) 61.1 GB
Too big Get file →

What GPU do you need for L3.3 70B Euryale v2.3 GGUF ooba?

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 L3.3 70B Euryale v2.3 GGUF ooba quant should you choose?

Q6_K (57.9 GB) is the middle option in this repository. Very close to the original quality for most uses, at a clearly larger size than 4-bit.

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 byHuzderu
FamilyEuryale
Licensellama3
Downloads (HF)6
Last updated2024-12-10

Frequently asked questions about L3.3 70B Euryale v2.3 GGUF ooba

How much VRAM does L3.3 70B Euryale v2.3 GGUF ooba need?

About 61.1 GB at Q6_K with an 8K context window. That is the 57.9 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 L3.3 70B Euryale v2.3 GGUF ooba on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 61.1 GB, so you would need a larger GPU or CPU offloading.

What is the file size of L3.3 70B Euryale v2.3 GGUF ooba GGUF?

It depends on the quant: Q6_K is 57.9 GB.

What context length does L3.3 70B Euryale v2.3 GGUF ooba 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 L3.3 70B Euryale v2.3 GGUF ooba GGUF?

The files are on Hugging Face in the Huzderu/L3.3-70B-Euryale-v2.3-GGUF-ooba repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does L3.3 70B Euryale v2.3 GGUF ooba use?

Hugging Face lists the license as llama3. 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 Huzderu

All by Huzderu →

More Euryale models

All Euryale →

Other large models

All large models →