SA

sarashina2.2 12B moe v0.1

SarashinaGGUF by DataPilotUpdated 2025-03-08
Download on Hugging Face
Parameters7.76B
Context8K
Layers32
Architecturellama
Smallest quant4.7 GB
Quick answer

sarashina2.2 12B moe v0.1 needs about 6.6 GB of memory at Q4_K_M (a 4.7 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 2 quants, from 4.7 GB (Q4_K_M) to 15.5 GB.

sarashina2.2 12B moe v0.1 is a 7.76B-parameter Sarashina model in GGUF format, quantized by DataPilot. Its trained context length is 8K tokens. The repository has 2 quant files, from 4.7 GB (Q4_K_M) to 15.5 GB.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M4.7 GB 6.6 GB
Fits Get file →
—15.5 GB 17.4 GB
Too big Get file →

What GPU do you need for sarashina2.2 12B 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: the best quant that fits is Q4_K_M (4.7 GB file, about 6.6 GB in use).
  • 12 GB VRAM: the best quant that fits is Q4_K_M (4.7 GB file, about 6.6 GB in use).
  • 16 GB VRAM: the best quant that fits is Q4_K_M (4.7 GB file, about 6.6 GB in use).
  • 24 GB VRAM: the best quant that fits is the main file (15.5 GB file, about 17.4 GB in use).

Which sarashina2.2 12B moe v0.1 quant should you choose?

Q4_K_M is the usual starting point for sarashina2.2 12B moe v0.1: it balances file size and quality well. Here it is a 4.7 GB file.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters7.76B (approximate, mixture of experts)
Layers32
Trained context8,192 tokens
KV cache (fp16)160 KB per token

Source

Quantized byDataPilot
FamilySarashina
Licensemit
Downloads (HF)11
Last updated2025-03-08

Frequently asked questions about sarashina2.2 12B moe v0.1

How much VRAM does sarashina2.2 12B moe v0.1 need?

About 6.6 GB at Q4_K_M with an 8K context window. That is the 4.7 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 12B moe v0.1 on an 8 GB GPU?

Yes, with Q4_K_M: the 4.7 GB file needs about 6.6 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of sarashina2.2 12B moe v0.1 GGUF?

It depends on the quant: Q4_K_M is 4.7 GB, file is 15.5 GB.

What context length does sarashina2.2 12B 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 12B moe v0.1 GGUF?

The files are on Hugging Face in the DataPilot/sarashina2.2-12B-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 12B 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 small models

All small models →