SA

sarashina2.2 24B moe v0.1

SarashinaGGUF by DataPilotUpdated 2025-03-08
Download on Hugging Face
Parameters16.6B
Context8K
Layers32
Architecturellama
Smallest quant10.1 GB
Quick answer

sarashina2.2 24B moe v0.1 needs about 11.9 GB of memory at Q4_K_M (a 10.1 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 2 quants, from 10.1 GB (Q4_K_M) to 33.1 GB.

sarashina2.2 24B moe v0.1 is a 16.6B-parameter Sarashina model in GGUF format, quantized by DataPilot. Its trained context length is 8K tokens. The repository has 2 quant files, from 10.1 GB (Q4_K_M) to 33.1 GB.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M10.1 GB 11.9 GB
Too big Get file →
—33.1 GB 35.0 GB
Too big Get file →

What GPU do you need for sarashina2.2 24B moe v0.1?

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: the best quant that fits is Q4_K_M (10.1 GB file, about 11.9 GB in use).
  • 16 GB VRAM: the best quant that fits is Q4_K_M (10.1 GB file, about 11.9 GB in use).
  • 24 GB VRAM: the best quant that fits is Q4_K_M (10.1 GB file, about 11.9 GB in use).
  • 32 GB VRAM: the best quant that fits is Q4_K_M (10.1 GB file, about 11.9 GB in use).
  • 48 GB VRAM: the best quant that fits is the main file (33.1 GB file, about 35.0 GB in use).

Which sarashina2.2 24B moe v0.1 quant should you choose?

Q4_K_M is the usual starting point for sarashina2.2 24B moe v0.1: it balances file size and quality well. Here it is a 10.1 GB file.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters16.6B (approximate, mixture of experts)
Layers32
Trained context8,192 tokens
KV cache (fp16)160 KB per token

Source

Quantized byDataPilot
FamilySarashina
Licensemit
Downloads (HF)57
Last updated2025-03-08

Frequently asked questions about sarashina2.2 24B moe v0.1

How much VRAM does sarashina2.2 24B moe v0.1 need?

About 11.9 GB at Q4_K_M with an 8K context window. That is the 10.1 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 sarashina2.2 24B moe v0.1 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 11.9 GB, so you would need a larger GPU or CPU offloading.

What is the file size of sarashina2.2 24B moe v0.1 GGUF?

It depends on the quant: Q4_K_M is 10.1 GB, file is 33.1 GB.

What context length does sarashina2.2 24B moe v0.1 support?

The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 1.3 GB at 8K and 1.3 GB at 8K.

Where can I download sarashina2.2 24B moe v0.1 GGUF?

The files are on Hugging Face in the DataPilot/sarashina2.2-24B-moe-v0.1-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 sarashina2.2 24B moe v0.1 use?

Hugging Face lists the license as mit. 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 DataPilot

All by DataPilot →

More Sarashina models

All Sarashina →

Other medium models

All medium models →