SM

SmallThinker 21BA3B Instruct

SmallthinkerGGUF by TiinyUpdated 2025-08-05
Download on Hugging Face
Parameters21.5B
Context16K
Layers52
Architecturesmallthinker
Smallest quant9.4 GB
Quick answer

SmallThinker 21BA3B Instruct needs about 14.5 GB of memory at Q4_K_M (a 13.1 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 26 quants, from 9.4 GB (Q3_K_S) to 43.0 GB (F16).

SmallThinker 21BA3B Instruct – 21.5B‑parameter MoE LLM for local deployment

SmallThinker 21BA3B Instruct is a 21.5B‑parameter Mixture‑of‑Experts model designed for on‑device inference. It supports 16384‑token context and is released under the apache‑2.0 license. The model is optimized for low‑memory, low‑latency use on consumer CPUs and GPUs.

Good at

  • Large context handling
  • Efficient on‑device inference
  • MoE architecture for reduced compute

Limits

  • No vision support
  • Requires 16384‑token context
  • Large memory for higher quants

Best for

  • Local chatbot applications
  • Personal data privacy use cases
  • Edge device AI

Who it’s for. Developers and researchers needing a high‑capacity language model that runs entirely on local hardware. The model is suitable for users with access to GPUs or CPUs that can handle the memory requirements of the chosen quantization.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q3_K_S9.4 GB 10.8 GB
Too big Get file →
Q3_K_S9.4 GB 10.8 GB
Too big Get file →
Q3_K10.4 GB 11.8 GB
Too big Get file →
Q3_K10.4 GB 11.8 GB
Too big Get file →
IQ4_XS11.6 GB 13.0 GB
Too big Get file →
IQ4_XS11.7 GB 13.1 GB
Too big Get file →
Q4_012.1 GB 13.5 GB
Too big Get file →
Q4_012.2 GB 13.6 GB
Too big Get file →
Q4_012.2 GB 13.6 GB
Too big Get file →
Q4_012.3 GB 13.7 GB
Too big Get file →
Q4_K_S12.3 GB 13.7 GB
Too big Get file →
Q4_K_S12.3 GB 13.7 GB
Too big Get file →
Q4_K_S12.3 GB 13.7 GB
Too big Get file →
IQ4_NL12.3 GB 13.7 GB
Too big Get file →
Q4_K13.1 GB 14.5 GB
Too big Get file →
Q4_K_M13.1 GB 14.5 GB
Too big Get file →
Q4_K13.1 GB 14.5 GB
Too big Get file →
Q4_113.6 GB 14.9 GB
Too big Get file →
Q4_113.6 GB 14.9 GB
Too big Get file →
Q5_K15.3 GB 16.7 GB
Too big Get file →
Q5_K15.3 GB 16.7 GB
Too big Get file →
Q6_K17.7 GB 19.0 GB
Too big Get file →
Q6_K17.7 GB 19.0 GB
Too big Get file →
Q8_022.9 GB 24.3 GB
Too big Get file →
Q8_022.9 GB 24.3 GB
Too big Get file →
F1643.0 GB 44.4 GB
Too big Get file →

For 8GB VRAM, use Q4_0 (file size 12.14 GB, estimated 13.5 GB memory at 8k context). For 12GB VRAM, Q4_K_S (12.33 GB, 13.7 GB memory) is suitable. For 16GB VRAM, Q5_K (15.31 GB, 16.7 GB memory) provides a balance between size and performance. Memory estimates are approximate.

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: 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 Q3_K (10.4 GB file, about 11.8 GB in use).
  • 16 GB VRAM: the best quant that fits is Q4_1 (13.6 GB file, about 14.9 GB in use).
  • 24 GB VRAM: the best quant that fits is Q6_K (17.7 GB file, about 19.0 GB in use).
  • 32 GB VRAM: the best quant that fits is Q8_0 (22.9 GB file, about 24.3 GB in use).
  • 48 GB VRAM: the best quant that fits is F16 (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 13.1 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 Q3_K_S at 9.4 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

Architecturesmallthinker
Parameters21.5B (approximate, mixture of experts)
Layers52
Trained context16,384 tokens
KV cache (fp16)104 KB per token

Source

Quantized byTiiny
Licenseapache-2.0
Downloads (HF)1,007
Last updated2025-08-05

Frequently asked questions about SmallThinker 21BA3B Instruct

How much VRAM does SmallThinker 21BA3B Instruct need?

About 14.5 GB at Q4_K_M with an 8K context window. That is the 13.1 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 SmallThinker 21BA3B Instruct on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 10.8 GB, so you would need a larger GPU or CPU offloading.

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

It depends on the quant: Q3_K_S is 9.4 GB, Q3_K_S is 9.4 GB, Q3_K is 10.4 GB, Q3_K is 10.4 GB, IQ4_XS is 11.6 GB, IQ4_XS is 11.7 GB and 20 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 Tiiny/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.

Can I run SmallThinker 21BA3B Instruct on 8GB VRAM?

Yes, the Q4_0 quantization requires about 13.5 GB memory at 8k context, which fits within 8GB VRAM with offloading or CPU fallback.

Does the model support vision tasks?

No, SmallThinker 21BA3B Instruct is a text‑only model with no vision capabilities.

What license does the model use?

The model is released under the apache‑2.0 license, allowing free use and modification.

Other GGUFs of SmallThinker-21BA3B-Instruct

Similar models

Browse all →

More from Tiiny

All by Tiiny →

More Smallthinker models

All Smallthinker →

Other medium models

All medium models →