MI

dolphin-2.7-mixtral-8x7b

MistralGGUF by NeoChen1024Updated 2024-09-17
Download on Hugging Face
Parameters46.7B
Context32K
Layers32
Architecturellama
Smallest quant21.4 GB
Quick answer

dolphin-2.7-mixtral-8x7b needs about 23.0 GB of memory at IQ3_M (a 21.4 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 2 quants, from 21.4 GB (IQ3_M) to 21.4 GB (IQ3_M). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

dolphin-2.7-mixtral-8x7b is a 46.7B-parameter Mistral model in GGUF format, quantized by NeoChen1024. Its trained context length is 32K tokens. The repository has 2 quant files, from 21.4 GB (IQ3_M) to 21.4 GB (IQ3_M).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ3_M21.4 GB 23.0 GB
Too big Get file →
IQ3_M21.4 GB 23.0 GB
Too big Get file →

What GPU do you need for dolphin-2.7-mixtral-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: the best quant that fits is IQ3_M (21.4 GB file, about 23.0 GB in use).

Which dolphin-2.7-mixtral-8x7b quant should you choose?

IQ3_M (21.4 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.

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 byNeoChen1024
FamilyMistral
Licenseapache-2.0
Downloads (HF)49
Last updated2024-09-17

Frequently asked questions about dolphin-2.7-mixtral-8x7b

How much VRAM does dolphin-2.7-mixtral-8x7b need?

About 23.0 GB at IQ3_M with an 8K context window. That is the 21.4 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 dolphin-2.7-mixtral-8x7b on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 23.0 GB, so you would need a larger GPU or CPU offloading.

What is the file size of dolphin-2.7-mixtral-8x7b GGUF?

It depends on the quant: IQ3_M is 21.4 GB, IQ3_M is 21.4 GB.

What context length does dolphin-2.7-mixtral-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 dolphin-2.7-mixtral-8x7b GGUF?

The files are on Hugging Face in the NeoChen1024/dolphin-2.7-mixtral-8x7b-GGUF-IQ3_M repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does dolphin-2.7-mixtral-8x7b 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.

Other GGUFs of dolphin-2.7-mixtral-8x7b

Similar models

Browse all →

More from NeoChen1024

All by NeoChen1024 →

More Mistral models

All Mistral →

Other large models

All large models →