SM

SmallThinker 3B Preview

SmallthinkerGGUF by quantflexUpdated 2025-01-01
Download on Hugging Face
Parameters3.09B
Context32K
Layers36
Architectureqwen2
Smallest quant2.0 GB
Quick answer

SmallThinker 3B Preview needs about 3.1 GB of memory at Q4_K_M (a 2.3 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 7 quants, from 2.0 GB (Q3_K_M) to 12.3 GB (F32). Longer context needs more: at 32K tokens the KV cache alone adds about 1.2 GB.

SmallThinker 3B Preview is a 3.09B-parameter Smallthinker model in GGUF format, quantized by quantflex. Its trained context length is 32K tokens. The repository has 7 quant files, from 2.0 GB (Q3_K_M) to 12.3 GB (F32).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q3_K_M2.0 GB 2.8 GB
Fits Get file →
Q4_K_M2.3 GB 3.1 GB
Fits Get file →
Q5_K_M2.6 GB 3.4 GB
Fits Get file →
Q6_K2.9 GB 3.7 GB
Fits Get file →
Q8_03.3 GB 4.1 GB
Fits Get file →
F166.2 GB 7.0 GB
Fits Get file →
F3212.3 GB 13.2 GB
Too big Get file →

What GPU do you need for SmallThinker 3B Preview?

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 Q6_K (2.9 GB file, about 3.7 GB in use).
  • 6 GB VRAM: the best quant that fits is Q8_0 (3.3 GB file, about 4.1 GB in use).
  • 8 GB VRAM: the best quant that fits is F16 (6.2 GB file, about 7.0 GB in use).
  • 12 GB VRAM: the best quant that fits is F16 (6.2 GB file, about 7.0 GB in use).
  • 16 GB VRAM: the best quant that fits is F32 (12.3 GB file, about 13.2 GB in use).

Which SmallThinker 3B Preview quant should you choose?

Q4_K_M is the usual starting point for SmallThinker 3B Preview: it balances file size and quality well. Here it is a 2.3 GB file.

The Q8_0 file is 3.3 GB, about 1.4 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_M at 2.0 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

Architectureqwen2
Parameters3.09B
Layers36
Trained context32,768 tokens
KV cache (fp16)36 KB per token

Source

Quantized byquantflex
Licenseother
Downloads (HF)191
Last updated2025-01-01

Frequently asked questions about SmallThinker 3B Preview

How much VRAM does SmallThinker 3B Preview need?

About 3.1 GB at Q4_K_M with an 8K context window. That is the 2.3 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 3B Preview on an 8 GB GPU?

Yes, with F16: the 6.2 GB file needs about 7.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of SmallThinker 3B Preview GGUF?

It depends on the quant: Q3_K_M is 2.0 GB, Q4_K_M is 2.3 GB, Q5_K_M is 2.6 GB, Q6_K is 2.9 GB, Q8_0 is 3.3 GB, F16 is 6.2 GB and 1 more.

What context length does SmallThinker 3B Preview support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 0.3 GB at 8K and 1.2 GB at 32K.

Where can I download SmallThinker 3B Preview GGUF?

The files are on Hugging Face in the quantflex/SmallThinker-3B-Preview-abliterated-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 3B Preview use?

Hugging Face lists the license as other. 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 SmallThinker-3B-Preview-abliterated

Similar models

Browse all →

More from quantflex

All by quantflex →

More Smallthinker models

All Smallthinker →

Other tiny models

All tiny models →