MI

Mixtral 8x22B v0.1 iMat

MistralGGUF by NexesQuantsUpdated 2024-04-19
Download on Hugging Face
Parameters141B
Context64K
Layers56
Architecturellama
Smallest quant30.4 GB
Quick answer

Mixtral 8x22B v0.1 iMat needs about 34.8 GB of memory at its main file (a 32.4 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 3 quants, from 30.4 GB to 33.1 GB. Longer context needs more: at 32K tokens the KV cache alone adds about 7.5 GB.

Mixtral 8x22B v0.1 iMat is a 141B-parameter Mistral model in GGUF format, quantized by NexesQuants. Its trained context length is 64K tokens. The repository has 3 quant files, from 30.4 GB to 33.1 GB.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—30.4 GB 32.8 GB
Too big Get file →
—32.4 GB 34.8 GB
Too big Get file →
—33.1 GB 35.5 GB
Too big Get file →

What GPU do you need for Mixtral 8x22B v0.1 iMat?

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: the best quant that fits is the main file (33.1 GB file, about 35.5 GB in use).

Which Mixtral 8x22B v0.1 iMat quant should you choose?

If memory is tight, the smallest file is the first one in the table at 30.4 GB, with the quality trade-offs that come with fewer bits.

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 byNexesQuants
FamilyMistral
Downloads (HF)32
Last updated2024-04-19

Frequently asked questions about Mixtral 8x22B v0.1 iMat

How much VRAM does Mixtral 8x22B v0.1 iMat need?

About 34.8 GB at its main file with an 8K context window. That is the 32.4 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 Mixtral 8x22B v0.1 iMat on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 32.8 GB, so you would need a larger GPU or CPU offloading.

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

It depends on the quant: file is 30.4 GB, file is 32.4 GB, file is 33.1 GB.

What context length does Mixtral 8x22B v0.1 iMat 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 v0.1 iMat GGUF?

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

Similar models

Browse all →

More from NexesQuants

All by NexesQuants →

More Mistral models

All Mistral →

Other large models

All large models →