MI

BagelMix 8x7B

MistralGGUF by Undi95Updated 2024-01-12
Download on Hugging Face
Parameters46.7B
Context32K
Layers32
Architecturellama
Smallest quant26.4 GB
Quick answer

BagelMix 8x7B needs about 33.8 GB of memory at Q5_0 (a 32.2 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 4 quants, from 26.4 GB (Q4_0) to 49.6 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

BagelMix 8x7B is a 46.7B-parameter Mistral model in GGUF format, quantized by Undi95. Its trained context length is 32K tokens. The repository has 4 quant files, from 26.4 GB (Q4_0) to 49.6 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_026.4 GB 28.0 GB
Too big Get file →
Q5_032.2 GB 33.8 GB
Too big Get file →
Q6_K38.4 GB 40.0 GB
Too big Get file →
Q8_049.6 GB 51.2 GB
Too big Get file →

What GPU do you need for BagelMix 8x7B?

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 Q4_0 (26.4 GB file, about 28.0 GB in use).
  • 48 GB VRAM: the best quant that fits is Q6_K (38.4 GB file, about 40.0 GB in use).

Which BagelMix 8x7B quant should you choose?

Q5_0 (32.2 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 Q4_0 at 26.4 GB, with the quality trade-offs that come with fewer bits. The usual sweet spot between file size and quality, and the quant most people start with.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters46.7B (approximate, mixture of experts)
Layers32
Trained context32,768 tokens
KV cache (fp16)128 KB per token

Source

Quantized byUndi95
FamilyMistral
Downloads (HF)15
Last updated2024-01-12

Frequently asked questions about BagelMix 8x7B

How much VRAM does BagelMix 8x7B need?

About 33.8 GB at Q5_0 with an 8K context window. That is the 32.2 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 BagelMix 8x7B on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 28.0 GB, so you would need a larger GPU or CPU offloading.

What is the file size of BagelMix 8x7B GGUF?

It depends on the quant: Q4_0 is 26.4 GB, Q5_0 is 32.2 GB, Q6_K is 38.4 GB, Q8_0 is 49.6 GB.

What context length does BagelMix 8x7B 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 BagelMix 8x7B GGUF?

The files are on Hugging Face in the Undi95/BagelMix-8x7B-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 BagelMix 8x7B use?

Hugging Face lists the license as cc-by-nc-4.0. 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 Mixtral-8x7B-Instruct-v0.1-LimaRP-ZLoss

Similar models

Browse all →

More from Undi95

All by Undi95 →

More Mistral models

All Mistral →

Other large models

All large models →