SM

SmallThinker-21BA3B-Instruct

SmallthinkerGGUF by MungertUpdated 2025-09-24
Download on Hugging Face
Parameters21.5B
Context16K
Layers52
Architecturesmallthinker
Smallest quant0.1 GB
Quick answer

SmallThinker-21BA3B-Instruct needs about 15.0 GB of memory at Q4_K_M (a 13.6 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 28 quants, from 0.1 GB to 43.0 GB (BF16).

SmallThinker-21BA3B-Instruct is a 21.5B-parameter Smallthinker model in GGUF format, quantized by Mungert. Its trained context length is 16K tokens. The repository has 28 quant files, from 0.1 GB to 43.0 GB (BF16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.1 GB 1.5 GB
Fits Get file →
IQ1_S5.7 GB 7.1 GB
Fits Get file →
IQ1_M6.2 GB 7.6 GB
Tight Get file →
IQ2_XXS6.5 GB 7.9 GB
Tight Get file →
IQ2_XS7.0 GB 8.3 GB
Too big Get file →
IQ2_S7.5 GB 8.8 GB
Too big Get file →
IQ2_M7.8 GB 9.2 GB
Too big Get file →
Q2_K_S8.2 GB 9.5 GB
Too big Get file →
Q2_K_M8.2 GB 9.6 GB
Too big Get file →
IQ3_XXS9.1 GB 10.5 GB
Too big Get file →
IQ3_XS9.2 GB 10.5 GB
Too big Get file →
IQ3_M10.3 GB 11.6 GB
Too big Get file →
Q3_K_S10.7 GB 12.1 GB
Too big Get file →
Q3_K_M10.9 GB 12.3 GB
Too big Get file →
IQ4_XS11.6 GB 13.0 GB
Too big Get file →
Q4_012.1 GB 13.5 GB
Too big Get file →
Q4_K_S12.9 GB 14.3 GB
Too big Get file →
Q4_113.5 GB 14.8 GB
Too big Get file →
Q4_K_M13.6 GB 15.0 GB
Too big Get file →
Q5_014.8 GB 16.2 GB
Too big Get file →
Q5_K_S15.5 GB 16.9 GB
Too big Get file →
Q5_K_M15.8 GB 17.2 GB
Too big Get file →
Q5_116.2 GB 17.5 GB
Too big Get file →
Q6_K_M17.7 GB 19.0 GB
Too big Get file →
Q8_022.9 GB 24.3 GB
Too big Get file →
BF1624.1 GB 25.5 GB
Too big Get file →
F1624.1 GB 25.5 GB
Too big Get file →
BF1643.0 GB 44.4 GB
Too big Get file →

What GPU do you need for SmallThinker-21BA3B-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 the main file (0.1 GB file, about 1.5 GB in use).
  • 6 GB VRAM: the best quant that fits is the main file (0.1 GB file, about 1.5 GB in use).
  • 8 GB VRAM: the best quant that fits is IQ2_XXS (6.5 GB file, about 7.9 GB in use).
  • 12 GB VRAM: the best quant that fits is IQ3_M (10.3 GB file, about 11.6 GB in use).
  • 16 GB VRAM: the best quant that fits is Q4_K_M (13.6 GB file, about 15.0 GB in use).
  • 24 GB VRAM: the best quant that fits is Q6_K_M (17.7 GB file, about 19.0 GB in use).
  • 32 GB VRAM: the best quant that fits is BF16 (24.1 GB file, about 25.5 GB in use).
  • 48 GB VRAM: the best quant that fits is BF16 (43.0 GB file, about 44.4 GB in use).

Which SmallThinker-21BA3B-Instruct quant should you choose?

Q4_K_M is the usual starting point for SmallThinker-21BA3B-Instruct: it balances file size and quality well. Here it is a 13.6 GB file.

The Q8_0 file is 22.9 GB, about 1.7 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 the first one in the table at 0.1 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
Parameters21.5B (approximate, mixture of experts)
Layers52
Trained context16,384 tokens
KV cache (fp16)104 KB per token

Source

Quantized byMungert
Licenseapache-2.0
Downloads (HF)382
Last updated2025-09-24

Frequently asked questions about SmallThinker-21BA3B-Instruct

How much VRAM does SmallThinker-21BA3B-Instruct need?

About 15.0 GB at Q4_K_M with an 8K context window. That is the 13.6 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-21BA3B-Instruct on an 8 GB GPU?

Yes, with IQ2_XXS: the 6.5 GB file needs about 7.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of SmallThinker-21BA3B-Instruct GGUF?

It depends on the quant: file is 0.1 GB, IQ1_S is 5.7 GB, IQ1_M is 6.2 GB, IQ2_XXS is 6.5 GB, IQ2_XS is 7.0 GB, IQ2_S is 7.5 GB and 22 more.

What context length does SmallThinker-21BA3B-Instruct support?

The GGUF header lists a trained context length of 16,384 tokens (16K). The KV cache grows with the context you use: about 0.9 GB at 8K and 1.7 GB at 16K.

Where can I download SmallThinker-21BA3B-Instruct GGUF?

The files are on Hugging Face in the Mungert/SmallThinker-21BA3B-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 SmallThinker-21BA3B-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.

Similar models

Browse all →

More from Mungert

All by Mungert →

More Smallthinker models

All Smallthinker →

Other medium models

All medium models →