MI

MistralTrix8x9B

MistralGGUF by hus960Updated 2024-04-25
Download on Hugging Face
Parameters58.3B
Context32K
Layers40
Architecturellama
Smallest quant21.6 GB
Quick answer

MistralTrix8x9B needs about 23.4 GB of memory at Q2_K (a 21.6 GB file) with an 8K context window, so it fits on a 24 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 5.4 GB.

MistralTrix8x9B is a 58.3B-parameter Mistral model in GGUF format, quantized by hus960. Its trained context length is 32K tokens. The repository has 1 quant file, from 21.6 GB (Q2_K) to 21.6 GB (Q2_K).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K21.6 GB 23.4 GB
Too big Get file →

What GPU do you need for MistralTrix8x9B?

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: the best quant that fits is Q2_K (21.6 GB file, about 23.4 GB in use).

Which MistralTrix8x9B quant should you choose?

Q2_K (21.6 GB) is the middle option in this repository. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters58.3B (approximate, mixture of experts)
Layers40
Trained context32,768 tokens
KV cache (fp16)160 KB per token

Source

Quantized byhus960
FamilyMistral
Licenseapache-2.0
Downloads (HF)9
Last updated2024-04-25

Frequently asked questions about MistralTrix8x9B

How much VRAM does MistralTrix8x9B need?

About 23.4 GB at Q2_K with an 8K context window. That is the 21.6 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 MistralTrix8x9B on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 23.4 GB, so you would need a larger GPU or CPU offloading.

What is the file size of MistralTrix8x9B GGUF?

It depends on the quant: Q2_K is 21.6 GB.

What context length does MistralTrix8x9B support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 1.3 GB at 8K and 5.4 GB at 32K.

Where can I download MistralTrix8x9B GGUF?

The files are on Hugging Face in the hus960/MistralTrix8x9B-Q2_K-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 MistralTrix8x9B 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 from hus960

All by hus960 →

More Mistral models

All Mistral →

Other large models

All large models →