MI

mixtral 8x22b v0.1 instruct oh

MistralGGUF by failspyUpdated 2024-04-13
Download on Hugging Face
Parameters141B
Context64K
Layers56
Architecturellama
Smallest quant85.6 GB
Quick answer

mixtral 8x22b v0.1 instruct oh needs about 88.0 GB of memory at Q4_K_M (a 85.6 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 4 quants, from 85.6 GB (Q4_K_M) to 149.4 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 7.5 GB.

mixtral 8x22b v0.1 instruct oh is a 141B-parameter Mistral model in GGUF format, quantized by failspy. Its trained context length is 64K tokens. The repository has 4 quant files, from 85.6 GB (Q4_K_M) to 149.4 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M85.6 GB (2 parts) 88.0 GB
Too big Get file →
Q5_K_M100.0 GB (3 parts) 102.3 GB
Too big Get file →
Q6_K_M115.5 GB (3 parts) 117.9 GB
Too big Get file →
Q8_0149.4 GB (4 parts) 151.8 GB
Too big Get file →

What GPU do you need for mixtral 8x22b v0.1 instruct oh?

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 v0.1 instruct oh quant should you choose?

Q4_K_M is the usual starting point for mixtral 8x22b v0.1 instruct oh: it balances file size and quality well. Here it is a 85.6 GB file.

The Q8_0 file is 149.4 GB, about 1.7 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.

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 byfailspy
FamilyMistral
Licenseapache-2.0
Downloads (HF)67
Last updated2024-04-13

Frequently asked questions about mixtral 8x22b v0.1 instruct oh

How much VRAM does mixtral 8x22b v0.1 instruct oh need?

About 88.0 GB at Q4_K_M with an 8K context window. That is the 85.6 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 instruct oh on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 88.0 GB, so you would need a larger GPU or CPU offloading.

What is the file size of mixtral 8x22b v0.1 instruct oh GGUF?

It depends on the quant: Q4_K_M is 85.6 GB, Q5_K_M is 100.0 GB, Q6_K_M is 115.5 GB, Q8_0 is 149.4 GB.

What context length does mixtral 8x22b v0.1 instruct oh 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 instruct oh GGUF?

The files are on Hugging Face in the failspy/mixtral-8x22b-v0.1-instruct-oh-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 mixtral 8x22b v0.1 instruct oh 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 Mixtral-8x22B-v0.1

Similar models

Browse all →

More from failspy

All by failspy →

More Mistral models

All Mistral →

Other large models

All large models →