MI

Mixtral 8x3B Random

MistralGGUF by minpeterUpdated 2025-07-31
Download on Hugging Face
Parameters19.9B
Context32K
Layers30
Architecturellama
Smallest quant12.2 GB
Quick answer

Mixtral 8x3B Random needs about 13.7 GB of memory at Q4_K_M (a 12.2 GB file) with an 8K context window, so it fits on a 16 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 4.0 GB.

Mixtral 8x3B Random is a 19.9B-parameter Mistral model in GGUF format, quantized by minpeter. Its trained context length is 32K tokens. The repository has 1 quant file, from 12.2 GB (Q4_K_M) to 12.2 GB (Q4_K_M).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M12.2 GB 13.7 GB
Too big Get file →

What GPU do you need for Mixtral 8x3B Random?

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: the best quant that fits is Q4_K_M (12.2 GB file, about 13.7 GB in use).

Which Mixtral 8x3B Random quant should you choose?

Q4_K_M is the usual starting point for Mixtral 8x3B Random: it balances file size and quality well. Here it is a 12.2 GB file.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters19.9B (approximate, mixture of experts)
Layers30
Trained context32,768 tokens
KV cache (fp16)120 KB per token

Source

Quantized byminpeter
FamilyMistral
Downloads (HF)9
Last updated2025-07-31

Frequently asked questions about Mixtral 8x3B Random

How much VRAM does Mixtral 8x3B Random need?

About 13.7 GB at Q4_K_M with an 8K context window. That is the 12.2 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 8x3B Random on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 13.7 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Mixtral 8x3B Random GGUF?

It depends on the quant: Q4_K_M is 12.2 GB.

What context length does Mixtral 8x3B Random support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 1.0 GB at 8K and 4.0 GB at 32K.

Where can I download Mixtral 8x3B Random GGUF?

The files are on Hugging Face in the minpeter/Mixtral-8x3B-Random-Q4_K_M-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 minpeter

All by minpeter →

More Mistral models

All Mistral →

Other medium models

All medium models →