SM

SmallThinker 4B A0.6B Instruct MXFP4 MOE

SmallthinkerGGUF by noctrexUpdated 2025-10-27
Download on Hugging Face
Parameters4.27B
Context32K
Layers—
Architecturesmallthinker
Smallest quant0.0 GB
Quick answer

SmallThinker 4B A0.6B Instruct MXFP4 MOE needs about 3.4 GB of memory at MXFP4_MOE (a 2.6 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 3 quants, from 0.0 GB to 2.6 GB (MXFP4_MOE).

SmallThinker 4B A0.6B Instruct MXFP4 MOE is a 4.27B-parameter Smallthinker model in GGUF format, quantized by noctrex. Its trained context length is 32K tokens. The repository has 3 quant files, from 0.0 GB to 2.6 GB (MXFP4_MOE).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 0.5 GB
Fits Get file →
MXFP4_MOE2.6 GB 3.4 GB
Fits Get file →
MXFP4_MOE2.6 GB 3.4 GB
Fits Get file →

What GPU do you need for SmallThinker 4B A0.6B Instruct MXFP4 MOE?

These figures add the file size, an fp16 KV cache at an 8K context window 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 MXFP4_MOE (2.6 GB file, about 3.4 GB in use).

Which SmallThinker 4B A0.6B Instruct MXFP4 MOE quant should you choose?

MXFP4_MOE (2.6 GB) is the middle option in this repository. Lower bit counts mean smaller files and more quality loss.

If memory is tight, the smallest file is the first one in the table at 0.0 GB, with the quality trade-offs that come with fewer bits.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturesmallthinker
Parameters4.27B
Trained context32,768 tokens

Source

Quantized bynoctrex
Downloads (HF)141
Last updated2025-10-27

Frequently asked questions about SmallThinker 4B A0.6B Instruct MXFP4 MOE

How much VRAM does SmallThinker 4B A0.6B Instruct MXFP4 MOE need?

About 3.4 GB at MXFP4_MOE with an 8K context window. That is the 2.6 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 SmallThinker 4B A0.6B Instruct MXFP4 MOE on an 8 GB GPU?

Yes, with MXFP4_MOE: the 2.6 GB file needs about 3.4 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of SmallThinker 4B A0.6B Instruct MXFP4 MOE GGUF?

It depends on the quant: file is 0.0 GB, MXFP4_MOE is 2.6 GB, MXFP4_MOE is 2.6 GB.

What context length does SmallThinker 4B A0.6B Instruct MXFP4 MOE support?

The GGUF header lists a trained context length of 32,768 tokens (32K).

Where can I download SmallThinker 4B A0.6B Instruct MXFP4 MOE GGUF?

The files are on Hugging Face in the noctrex/SmallThinker-4B-A0.6B-Instruct-MXFP4_MOE-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 SmallThinker-4BA0.6B-Instruct

Similar models

Browse all →

More from noctrex

All by noctrex →

Other small models

All small models →