MI

Mistral Large Extra i1

MistralGGUF by mradermacherUpdated 2024-09-05
Download on Hugging Face
Parameters195B
Context128K
Layers140
Architecturellama
Smallest quant41.0 GB
Quick answer

Mistral Large Extra i1 needs about 46.2 GB of memory at IQ1_S (a 41.0 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 2 quants, from 41.0 GB (IQ1_S) to 44.9 GB (IQ1_M). Longer context needs more: at 32K tokens the KV cache alone adds about 18.8 GB.

Mistral Large Extra i1 is a 195B-parameter Mistral model in GGUF format, quantized by mradermacher. Its trained context length is 128K tokens. The repository has 2 quant files, from 41.0 GB (IQ1_S) to 44.9 GB (IQ1_M).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S41.0 GB 46.2 GB
Too big Get file →
IQ1_M44.9 GB 50.1 GB
Too big Get file →

What GPU do you need for Mistral Large Extra i1?

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 IQ1_S (41.0 GB file, about 46.2 GB in use).

Which Mistral Large Extra i1 quant should you choose?

IQ1_S (41.0 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
Parameters195B
Layers140
Trained context131,072 tokens
KV cache (fp16)560 KB per token

Source

Quantized bymradermacher
FamilyMistral
Downloads (HF)48
Last updated2024-09-05

Frequently asked questions about Mistral Large Extra i1

How much VRAM does Mistral Large Extra i1 need?

About 46.2 GB at IQ1_S with an 8K context window. That is the 41.0 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 Mistral Large Extra i1 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 46.2 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Mistral Large Extra i1 GGUF?

It depends on the quant: IQ1_S is 41.0 GB, IQ1_M is 44.9 GB.

What context length does Mistral Large Extra i1 support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 4.7 GB at 8K and 18.8 GB at 32K.

Where can I download Mistral Large Extra i1 GGUF?

The files are on Hugging Face in the mradermacher/Mistral-Large-Extra-i1-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 mradermacher

All by mradermacher →

More Mistral models

All Mistral →

Other large models

All large models →