MI

mixtral 4x7b instruct code

MistralGGUF by Denath-KhorUpdated 2024-03-21
Download on Hugging Face
Parameters24.2B
Context32K
Layers32
Architecturellama
Smallest quant25.7 GB
Quick answer

mixtral 4x7b instruct code needs about 27.2 GB of memory at Q8_0 (a 25.7 GB file) with an 8K context window, so it fits on a 32 GB GPU. This repository has 2 quants, from 25.7 GB (Q8_0) to 48.3 GB. Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

mixtral 4x7b instruct code is a 24.2B-parameter Mistral model in GGUF format, quantized by Denath-Khor. Its trained context length is 32K tokens. The repository has 2 quant files, from 25.7 GB (Q8_0) to 48.3 GB.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q8_025.7 GB 27.2 GB
Too big Get file →
—48.3 GB 49.9 GB
Too big Get file →

What GPU do you need for mixtral 4x7b instruct code?

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 Q8_0 (25.7 GB file, about 27.2 GB in use).
  • 48 GB VRAM: the best quant that fits is Q8_0 (25.7 GB file, about 27.2 GB in use).

Which mixtral 4x7b instruct code quant should you choose?

Q8_0 (25.7 GB) is the middle option in this repository. Close to lossless. It costs roughly twice the memory of a 4-bit file, so it suits cases where you have plenty of VRAM.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters24.2B (approximate, mixture of experts)
Layers32
Trained context32,768 tokens
KV cache (fp16)128 KB per token

Source

Quantized byDenath-Khor
FamilyMistral
Downloads (HF)28
Last updated2024-03-21

Frequently asked questions about mixtral 4x7b instruct code

How much VRAM does mixtral 4x7b instruct code need?

About 27.2 GB at Q8_0 with an 8K context window. That is the 25.7 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 4x7b instruct code on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 27.2 GB, so you would need a larger GPU or CPU offloading.

What is the file size of mixtral 4x7b instruct code GGUF?

It depends on the quant: Q8_0 is 25.7 GB, file is 48.3 GB.

What context length does mixtral 4x7b instruct code 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 mixtral 4x7b instruct code GGUF?

The files are on Hugging Face in the Denath-Khor/mixtral-4x7b-instruct-code-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 Denath-Khor

All by Denath-Khor →

More Mistral models

All Mistral →

Other medium models

All medium models →