KA

Kaidol Thinking Sft 4b

KaidolGGUF by mradermacherUpdated 2025-12-16
Download on Hugging Face
Parameters4.41B
Context256K
Layers36
Architectureqwen3
Smallest quant0.0 GB
Quick answer

Kaidol Thinking Sft 4b needs about 4.4 GB of memory at Q4_K_M (a 2.7 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 25 quants, from 0.0 GB to 3.6 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 4.8 GB.

Kaidol Thinking Sft 4b – a 4.41B Qwen3 model fine‑tuned for structured reasoning and tool use

Kaidol Thinking Sft 4b is a 4.41B parameter Qwen3 model fine‑tuned for structured reasoning and tool usage. It is released under Apache‑2.0 and supports a 262144 token context window. The model is available in multiple GGUF quantizations.

Good at

  • Structured reasoning
  • Tool integration
  • Policy compliance

Limits

  • No vision support
  • Large context requires high VRAM
  • License is Apache‑2.0

Best for

  • Chatbots needing reasoning steps
  • Tool‑enabled assistants
  • Edge‑case robust dialogue

Who it’s for. Developers building chat interfaces that require structured reasoning and tool calls. The model is suitable for applications where policy compliance and edge‑case robustness are important.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 1.7 GB
Fits Get file →
IQ1_S1.2 GB 2.9 GB
Fits Get file →
IQ1_M1.3 GB 3.0 GB
Fits Get file →
IQ2_XXS1.4 GB 3.1 GB
Fits Get file →
IQ2_XS1.5 GB 3.2 GB
Fits Get file →
IQ2_S1.6 GB 3.3 GB
Fits Get file →
IQ2_M1.7 GB 3.4 GB
Fits Get file →
Q2_K_S1.7 GB 3.4 GB
Fits Get file →
Q2_K1.8 GB 3.5 GB
Fits Get file →
IQ3_XXS1.8 GB 3.5 GB
Fits Get file →
IQ3_XS2.0 GB 3.7 GB
Fits Get file →
Q3_K_S2.1 GB 3.8 GB
Fits Get file →
IQ3_S2.1 GB 3.8 GB
Fits Get file →
IQ3_M2.1 GB 3.8 GB
Fits Get file →
Q3_K_M2.2 GB 3.9 GB
Fits Get file →
Q3_K_L2.4 GB 4.1 GB
Fits Get file →
IQ4_XS2.5 GB 4.2 GB
Fits Get file →
Q4_02.6 GB 4.3 GB
Fits Get file →
IQ4_NL2.6 GB 4.3 GB
Fits Get file →
Q4_K_S2.6 GB 4.3 GB
Fits Get file →
Q4_K_M2.7 GB 4.4 GB
Fits Get file →
Q4_12.8 GB 4.5 GB
Fits Get file →
Q5_K_S3.1 GB 4.8 GB
Fits Get file →
Q5_K_M3.2 GB 4.9 GB
Fits Get file →
Q6_K3.6 GB 5.3 GB
Fits Get file →

For 8 GB VRAM, use Q4_K_M (file size 2.72 GB, estimated 4.4 GB memory). For 12 GB VRAM, Q5_K_M (3.16 GB, 4.9 GB memory) offers higher quality. For 16 GB VRAM, Q6_K (3.62 GB, 5.3 GB memory) gives the best performance.

What GPU do you need for Kaidol Thinking Sft 4b?

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 Q3_K_M (2.2 GB file, about 3.9 GB in use).
  • 6 GB VRAM: the best quant that fits is Q6_K (3.6 GB file, about 5.3 GB in use).

Which Kaidol Thinking Sft 4b quant should you choose?

Q4_K_M is the usual starting point for Kaidol Thinking Sft 4b: it balances file size and quality well. Here it is a 2.7 GB file.

If memory is tight, the smallest file is the first one in the table at 0.0 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

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

Source

Quantized bymradermacher
FamilyKaidol
Licenseapache-2.0
Downloads (HF)1,051
Last updated2025-12-16

Frequently asked questions about Kaidol Thinking Sft 4b

How much VRAM does Kaidol Thinking Sft 4b need?

About 4.4 GB at Q4_K_M with an 8K context window. That is the 2.7 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 Kaidol Thinking Sft 4b on an 8 GB GPU?

Yes, with Q6_K: the 3.6 GB file needs about 5.3 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Kaidol Thinking Sft 4b GGUF?

It depends on the quant: file is 0.0 GB, IQ1_S is 1.2 GB, IQ1_M is 1.3 GB, IQ2_XXS is 1.4 GB, IQ2_XS is 1.5 GB, IQ2_S is 1.6 GB and 19 more.

What context length does Kaidol Thinking Sft 4b 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 Kaidol Thinking Sft 4b GGUF?

The files are on Hugging Face in the mradermacher/kaidol-thinking-sft-4b-i1-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 Kaidol Thinking Sft 4b 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, use the Q4_K_M quant which requires about 4.4 GB VRAM at 8 k context.

Does this model support vision?

No, the model has no vision capability.

What license applies?

The model is released under Apache‑2.0.

Other GGUFs of kaidol-thinking-sft-4b

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Kaidol models

All Kaidol →

Other small models

All small models →