LL

openbuddy llama3.3 70b v24.2q

LlamaGGUF by OpenBuddyUpdated 2024-12-23
Download on Hugging Face
Parameters70.6B
Context128K
Layers80
Architecturellama
Smallest quant26.4 GB
Quick answer

openbuddy llama3.3 70b v24.2q needs about 37.5 GB of memory at Q3_K (a 34.3 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 3 quants, from 26.4 GB (Q2_K) to 42.5 GB (Q4_K). Longer context needs more: at 32K tokens the KV cache alone adds about 10.7 GB.

openbuddy llama3.3 70b v24.2q is a 70.6B-parameter Llama model in GGUF format, quantized by OpenBuddy. Its trained context length is 128K tokens. The repository has 3 quant files, from 26.4 GB (Q2_K) to 42.5 GB (Q4_K).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K26.4 GB 29.6 GB
Too big Get file →
Q3_K34.3 GB 37.5 GB
Too big Get file →
Q4_K42.5 GB 45.7 GB
Too big Get file →

What GPU do you need for openbuddy llama3.3 70b v24.2q?

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: the best quant that fits is Q2_K (26.4 GB file, about 29.6 GB in use).
  • 48 GB VRAM: the best quant that fits is Q4_K (42.5 GB file, about 45.7 GB in use).

Which openbuddy llama3.3 70b v24.2q quant should you choose?

Q3_K (34.3 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.

If memory is tight, the smallest file is Q2_K at 26.4 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 byOpenBuddy
FamilyLlama
Licensellama3.3
Downloads (HF)57
Last updated2024-12-23

Frequently asked questions about openbuddy llama3.3 70b v24.2q

How much VRAM does openbuddy llama3.3 70b v24.2q need?

About 37.5 GB at Q3_K with an 8K context window. That is the 34.3 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 llama3.3 70b v24.2q on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 29.6 GB, so you would need a larger GPU or CPU offloading.

What is the file size of openbuddy llama3.3 70b v24.2q GGUF?

It depends on the quant: Q2_K is 26.4 GB, Q3_K is 34.3 GB, Q4_K is 42.5 GB.

What context length does openbuddy llama3.3 70b v24.2q 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 openbuddy llama3.3 70b v24.2q GGUF?

The files are on Hugging Face in the OpenBuddy/openbuddy-llama3.3-70b-v24.2q-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 llama3.3 70b v24.2q use?

Hugging Face lists the license as llama3.3. 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 openbuddy-llama3.3-70b-v24.1-131k

Similar models

Browse all →

More from OpenBuddy

All by OpenBuddy →

More Llama models

All Llama →

Other large models

All large models →