TY

typhoon si med thinking 4b research preview

TyphoonGGUF by terasutUpdated 2026-01-21
Download on Hugging Face
Parameters4.41B
Context256K
Layers36
Architectureqwen3
Smallest quant4.7 GB
Quick answer

typhoon si med thinking 4b research preview needs about 6.4 GB of memory at Q8_0 (a 4.7 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 2 quants, from 4.7 GB (Q8_0) to 8.8 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 4.8 GB.

typhoon si med thinking 4b research preview is a 4.41B-parameter Typhoon model in GGUF format, quantized by terasut. Its trained context length is 256K tokens. The repository has 2 quant files, from 4.7 GB (Q8_0) to 8.8 GB (BF16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q8_04.7 GB 6.4 GB
Fits Get file →
BF168.8 GB 10.5 GB
Too big Get file →

What GPU do you need for typhoon si med thinking 4b research 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: no quant fits at an 8K context.
  • 6 GB VRAM: no quant fits at an 8K context.
  • 8 GB VRAM: the best quant that fits is Q8_0 (4.7 GB file, about 6.4 GB in use).
  • 12 GB VRAM: the best quant that fits is BF16 (8.8 GB file, about 10.5 GB in use).

Which typhoon si med thinking 4b research preview quant should you choose?

Q8_0 (4.7 GB) is the middle option in this repository. Close to lossless. It costs roughly twice the memory of a 4-bit file, so it suits cases where you have plenty of VRAM.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen3
Parameters4.41B
Layers36
Trained context262,144 tokens
KV cache (fp16)144 KB per token

Frequently asked questions about typhoon si med thinking 4b research preview

How much VRAM does typhoon si med thinking 4b research preview need?

About 6.4 GB at Q8_0 with an 8K context window. That is the 4.7 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 typhoon si med thinking 4b research preview on an 8 GB GPU?

Yes, with Q8_0: the 4.7 GB file needs about 6.4 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of typhoon si med thinking 4b research preview GGUF?

It depends on the quant: Q8_0 is 4.7 GB, BF16 is 8.8 GB.

What context length does typhoon si med thinking 4b research preview support?

The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 1.2 GB at 8K and 4.8 GB at 32K.

Where can I download typhoon si med thinking 4b research preview GGUF?

The files are on Hugging Face in the terasut/typhoon-si-med-thinking-4b-research-preview-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 typhoon si med thinking 4b research preview 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 typhoon-si-med-thinking-4b-research-preview

Similar models

Browse all →

More from terasut

All by terasut →

More Typhoon models

All Typhoon →

Other small models

All small models →