MI

letta

MistralGGUF by minchyeomUpdated 2024-10-17
Download on Hugging Face
Parameters22.2B
Context32K
Layers56
Architecturellama
Smallest quant23.6 GB
Quick answer

letta needs about 26.0 GB of memory at Q8_0 (a 23.6 GB file) with an 8K context window, so it fits on a 32 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 7.5 GB.

letta is a 22.2B-parameter Mistral model in GGUF format, quantized by minchyeom. Its trained context length is 32K tokens. The repository has 1 quant file, from 23.6 GB (Q8_0) to 23.6 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q8_023.6 GB 26.0 GB
Too big Get file →

What GPU do you need for letta?

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 (23.6 GB file, about 26.0 GB in use).

Which letta quant should you choose?

Q8_0 (23.6 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
Parameters22.2B
Layers56
Trained context32,768 tokens
KV cache (fp16)224 KB per token

Source

Quantized byminchyeom
FamilyMistral
Downloads (HF)16
Last updated2024-10-17

Frequently asked questions about letta

How much VRAM does letta need?

About 26.0 GB at Q8_0 with an 8K context window. That is the 23.6 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 letta on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 26.0 GB, so you would need a larger GPU or CPU offloading.

What is the file size of letta GGUF?

It depends on the quant: Q8_0 is 23.6 GB.

What context length does letta support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 1.9 GB at 8K and 7.5 GB at 32K.

Where can I download letta GGUF?

The files are on Hugging Face in the minchyeom/letta-gguf repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Other GGUFs of Mistral-Small-Instruct-2409

Similar models

Browse all →

More from minchyeom

All by minchyeom →

More Mistral models

All Mistral →

Other medium models

All medium models →