SA

SakaMoe 3x1.6B Instruct

SakamoeGGUF by mradermacherUpdated 2025-02-10
Download on Hugging Face
Parameters1.57B
Context32K
Layers24
Architectureqwen2moe
Smallest quant0.9 GB
Quick answer

SakaMoe 3x1.6B Instruct needs about 1.7 GB of memory at Q4_K_M (a 1.1 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 12 quants, from 0.9 GB (Q3_K_S) to 3.1 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 0.4 GB.

SakaMoe 3x1.6B Instruct is a 1.57B-parameter Sakamoe model in GGUF format, quantized by mradermacher. Its trained context length is 32K tokens. The repository has 12 quant files, from 0.9 GB (Q3_K_S) to 3.1 GB (F16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q3_K_S0.9 GB 1.5 GB
Fits Get file →
Q2_K0.9 GB 1.5 GB
Fits Get file →
IQ4_XS1.0 GB 1.6 GB
Fits Get file →
Q3_K_M1.0 GB 1.6 GB
Fits Get file →
Q3_K_L1.0 GB 1.6 GB
Fits Get file →
Q4_K_S1.1 GB 1.7 GB
Fits Get file →
Q4_K_M1.1 GB 1.7 GB
Fits Get file →
Q5_K_S1.2 GB 1.8 GB
Fits Get file →
Q5_K_M1.2 GB 1.8 GB
Fits Get file →
Q6_K1.6 GB 2.2 GB
Fits Get file →
Q8_01.7 GB 2.3 GB
Fits Get file →
F163.1 GB 3.8 GB
Fits Get file →

What GPU do you need for SakaMoe 3x1.6B Instruct?

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: the best quant that fits is F16 (3.1 GB file, about 3.8 GB in use).

Which SakaMoe 3x1.6B Instruct quant should you choose?

Q4_K_M is the usual starting point for SakaMoe 3x1.6B Instruct: it balances file size and quality well. Here it is a 1.1 GB file.

The Q8_0 file is 1.7 GB, about 1.5 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.

If memory is tight, the smallest file is Q3_K_S at 0.9 GB, with the quality trade-offs that come with fewer bits. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen2moe
Parameters1.57B (approximate, mixture of experts)
Layers24
Trained context32,768 tokens
KV cache (fp16)12 KB per token

Source

Quantized bymradermacher
FamilySakamoe
Licenseapache-2.0
Downloads (HF)55
Last updated2025-02-10

Frequently asked questions about SakaMoe 3x1.6B Instruct

How much VRAM does SakaMoe 3x1.6B Instruct need?

About 1.7 GB at Q4_K_M with an 8K context window. That is the 1.1 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 SakaMoe 3x1.6B Instruct on an 8 GB GPU?

Yes, with F16: the 3.1 GB file needs about 3.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of SakaMoe 3x1.6B Instruct GGUF?

It depends on the quant: Q3_K_S is 0.9 GB, Q2_K is 0.9 GB, IQ4_XS is 1.0 GB, Q3_K_M is 1.0 GB, Q3_K_L is 1.0 GB, Q4_K_S is 1.1 GB and 6 more.

What context length does SakaMoe 3x1.6B Instruct support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 0.1 GB at 8K and 0.4 GB at 32K.

Where can I download SakaMoe 3x1.6B Instruct GGUF?

The files are on Hugging Face in the mradermacher/SakaMoe-3x1.6B-Instruct-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 SakaMoe 3x1.6B Instruct 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.

Other GGUFs of SakaMoe-3x1.6B-Instruct

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Sakamoe models

All Sakamoe →

Other tiny models

All tiny models →