QW

scb10x/typhoon2.5-qwen3-4b-preview

QwenGGUF by typhoon-aiUpdated 2026-06-11
Download on Hugging Face
Parameters4.02B
Context256K
Layers36
Architectureqwen3
Smallest quant2.5 GB
Quick answer

scb10x/typhoon2.5-qwen3-4b-preview needs about 4.2 GB of memory at Q4_K_M (a 2.5 GB file) with an 8K context window, so it fits on a 6 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 4.8 GB.

4B Thai‑English instruct model based on Qwen3

Typhoon2.5‑Qwen3‑4B is a 4.02 billion‑parameter instruct decoder‑only model. It supports Thai and English, has a 262144‑token context length, and includes function‑calling capabilities.

Good at

  • Thai language generation
  • English text completion
  • Instruct‑style dialogue

Limits

  • No vision support
  • Requires 8 k context for memory estimate
  • Apache 2.0 license

Best for

  • Chatbots in Thai or English
  • Content creation in Southeast Asia
  • Educational tools for Thai language

Who it’s for. Developers building multilingual applications that need Thai and English support. The model is suitable for teams that can manage the 4.2 GB memory requirement at 8 k context and comply with the Apache 2.0 license.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M2.5 GB 4.2 GB
Fits Get file →

For 8 GB VRAM use the Q4_K_M quant. The 2.5 GB file requires about 4.2 GB of RAM at 8 k context. If you have less memory, consider a higher‑compression quant, but it is not listed here.

What GPU do you need for scb10x/typhoon2.5-qwen3-4b-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: the best quant that fits is Q4_K_M (2.5 GB file, about 4.2 GB in use).

Which scb10x/typhoon2.5-qwen3-4b-preview quant should you choose?

Q4_K_M is the usual starting point for scb10x/typhoon2.5-qwen3-4b-preview: it balances file size and quality well. Here it is a 2.5 GB file.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen3
Parameters4.02B
Layers36
Trained context262,144 tokens
KV cache (fp16)144 KB per token

Source

Quantized bytyphoon-ai
FamilyQwen
Licenseapache-2.0
Downloads (HF)705
Last updated2026-06-11

Frequently asked questions about scb10x/typhoon2.5-qwen3-4b-preview

How much VRAM does scb10x/typhoon2.5-qwen3-4b-preview need?

About 4.2 GB at Q4_K_M with an 8K context window. That is the 2.5 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 scb10x/typhoon2.5-qwen3-4b-preview on an 8 GB GPU?

Yes, with Q4_K_M: the 2.5 GB file needs about 4.2 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of scb10x/typhoon2.5-qwen3-4b-preview GGUF?

It depends on the quant: Q4_K_M is 2.5 GB.

What context length does scb10x/typhoon2.5-qwen3-4b-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 scb10x/typhoon2.5-qwen3-4b-preview GGUF?

The files are on Hugging Face in the typhoon-ai/typhoon2.5-qwen3-4b-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 scb10x/typhoon2.5-qwen3-4b-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.

Can I run this model on 8 GB VRAM?

Yes, the Q4_K_M quant uses 2.5 GB of VRAM and requires about 4.2 GB of RAM at 8 k context.

Does it support vision tasks?

No, the model has no vision capabilities.

What license applies?

The model is released under the Apache 2.0 license.

Other GGUFs of typhoon2.5-qwen3-4b

Similar models

Browse all →

More from typhoon-ai

All by typhoon-ai →

More Qwen models

All Qwen →

Other small models

All small models →