BR

BreeXe-8x7B-Inst

BreexeGGUF by PenutChenUpdated 2024-08-09
Download on Hugging Face
Parameters46.9B
Context32K
Layers32
Architecturellama
Smallest quant17.5 GB
Quick answer

BreeXe-8x7B-Inst needs about 35.0 GB of memory at Q5_K (a 33.4 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 7 quants, from 17.5 GB (Q2_K) to 93.9 GB. Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

BreeXe-8x7B-Inst is a 46.9B-parameter Breexe model in GGUF format, quantized by PenutChen. Its trained context length is 32K tokens. The repository has 7 quant files, from 17.5 GB (Q2_K) to 93.9 GB.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K17.5 GB 19.0 GB
Too big Get file →
Q3_K22.7 GB 24.3 GB
Too big Get file →
Q4_K28.6 GB 30.2 GB
Too big Get file →
Q5_K33.4 GB 35.0 GB
Too big Get file →
Q6_K38.6 GB 40.2 GB
Too big Get file →
Q8_049.9 GB 51.5 GB
Too big Get file →
—93.9 GB (2 parts) 95.5 GB
Too big Get file →

What GPU do you need for BreeXe-8x7B-Inst?

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 Q2_K (17.5 GB file, about 19.0 GB in use).
  • 32 GB VRAM: the best quant that fits is Q4_K (28.6 GB file, about 30.2 GB in use).
  • 48 GB VRAM: the best quant that fits is Q6_K (38.6 GB file, about 40.2 GB in use).

Which BreeXe-8x7B-Inst quant should you choose?

Q5_K (33.4 GB) is the middle option in this repository. Closer to the original model than 4-bit, for a moderate increase in size. A good pick when you have memory to spare.

If memory is tight, the smallest file is Q2_K at 17.5 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
Parameters46.9B (approximate, mixture of experts)
Layers32
Trained context32,768 tokens
KV cache (fp16)128 KB per token

Source

Quantized byPenutChen
FamilyBreexe
Licenseapache-2.0
Downloads (HF)51
Last updated2024-08-09

Frequently asked questions about BreeXe-8x7B-Inst

How much VRAM does BreeXe-8x7B-Inst need?

About 35.0 GB at Q5_K with an 8K context window. That is the 33.4 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 BreeXe-8x7B-Inst on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 19.0 GB, so you would need a larger GPU or CPU offloading.

What is the file size of BreeXe-8x7B-Inst GGUF?

It depends on the quant: Q2_K is 17.5 GB, Q3_K is 22.7 GB, Q4_K is 28.6 GB, Q5_K is 33.4 GB, Q6_K is 38.6 GB, Q8_0 is 49.9 GB and 1 more.

What context length does BreeXe-8x7B-Inst support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.3 GB at 32K.

Where can I download BreeXe-8x7B-Inst GGUF?

The files are on Hugging Face in the PenutChen/Breexe-8x7B-Instruct-v0_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 BreeXe-8x7B-Inst use?

Hugging Face lists the license as apache-2.0. 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 PenutChen

All by PenutChen →

More Breexe models

All Breexe →

Other large models

All large models →