MI

Mixtral 8x22B Instruct v0.1 GGUF imatrix

MistralGGUF by actually-a-catUpdated 2024-04-18
Download on Hugging Face
Parameters141B
Context64K
Layers56
Architecturellama
Smallest quant58.2 GB
Quick answer

Mixtral 8x22B Instruct v0.1 GGUF imatrix needs about 77.9 GB of memory at IQ4_XS (a 75.5 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 4 quants, from 58.2 GB (IQ3_XS) to 115.5 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 7.5 GB.

Mixtral 8x22B Instruct v0.1 GGUF imatrix is a 141B-parameter Mistral model in GGUF format, quantized by actually-a-cat. Its trained context length is 64K tokens. The repository has 4 quant files, from 58.2 GB (IQ3_XS) to 115.5 GB (Q6_K).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ3_XS58.2 GB (3 parts) 60.6 GB
Too big Get file →
IQ4_XS75.5 GB (4 parts) 77.9 GB
Too big Get file →
Q5_K_M100.0 GB (5 parts) 102.4 GB
Too big Get file →
Q6_K115.5 GB (6 parts) 117.9 GB
Too big Get file →

What GPU do you need for Mixtral 8x22B Instruct v0.1 GGUF imatrix?

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 Mixtral 8x22B Instruct v0.1 GGUF imatrix quant should you choose?

IQ4_XS (75.5 GB) is the middle option in this repository. The usual sweet spot between file size and quality, and the quant most people start with.

If memory is tight, the smallest file is IQ3_XS at 58.2 GB, with the quality trade-offs that come with fewer bits. 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
Parameters141B (approximate, mixture of experts)
Layers56
Trained context65,536 tokens
KV cache (fp16)224 KB per token

Source

Quantized byactually-a-cat
FamilyMistral
Licenseapache-2.0
Downloads (HF)50
Last updated2024-04-18

Frequently asked questions about Mixtral 8x22B Instruct v0.1 GGUF imatrix

How much VRAM does Mixtral 8x22B Instruct v0.1 GGUF imatrix need?

About 77.9 GB at IQ4_XS with an 8K context window. That is the 75.5 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 Mixtral 8x22B Instruct v0.1 GGUF imatrix on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 60.6 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Mixtral 8x22B Instruct v0.1 GGUF imatrix GGUF?

It depends on the quant: IQ3_XS is 58.2 GB, IQ4_XS is 75.5 GB, Q5_K_M is 100.0 GB, Q6_K is 115.5 GB.

What context length does Mixtral 8x22B Instruct v0.1 GGUF imatrix support?

The GGUF header lists a trained context length of 65,536 tokens (64K). The KV cache grows with the context you use: about 1.9 GB at 8K and 7.5 GB at 32K.

Where can I download Mixtral 8x22B Instruct v0.1 GGUF imatrix GGUF?

The files are on Hugging Face in the actually-a-cat/Mixtral-8x22B-Instruct-v0.1-GGUF-imatrix repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does Mixtral 8x22B Instruct v0.1 GGUF imatrix 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 Mistral models

All Mistral →

Other large models

All large models →