NA

Nanbeige4 3B Thinking Ties

NanbeigeGGUF by mradermacherUpdated 2025-12-22
Download on Hugging Face
Parameters3.93B
Context64K
Layers32
Architecturellama
Smallest quant0.0 GB
Quick answer

Nanbeige4 3B Thinking Ties needs about 3.5 GB of memory at Q4_K_M (a 2.4 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 25 quants, from 0.0 GB to 3.2 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 2.1 GB.

Nanbeige4 3B Thinking Ties is a 3.93B-parameter Nanbeige model in GGUF format, quantized by mradermacher. Its trained context length is 64K tokens. The repository has 25 quant files, from 0.0 GB to 3.2 GB (Q6_K).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 1.0 GB
Fits Get file →
IQ1_S1.1 GB 2.1 GB
Fits Get file →
IQ1_M1.1 GB 2.2 GB
Fits Get file →
IQ2_XXS1.3 GB 2.3 GB
Fits Get file →
IQ2_XS1.3 GB 2.4 GB
Fits Get file →
IQ2_S1.4 GB 2.5 GB
Fits Get file →
IQ2_M1.5 GB 2.5 GB
Fits Get file →
Q2_K_S1.5 GB 2.6 GB
Fits Get file →
Q2_K1.6 GB 2.7 GB
Fits Get file →
IQ3_XXS1.7 GB 2.7 GB
Fits Get file →
IQ3_XS1.8 GB 2.8 GB
Fits Get file →
Q3_K_S1.9 GB 2.9 GB
Fits Get file →
IQ3_S1.9 GB 2.9 GB
Fits Get file →
IQ3_M1.9 GB 2.9 GB
Fits Get file →
Q3_K_M2.0 GB 3.1 GB
Fits Get file →
Q3_K_L2.1 GB 3.2 GB
Fits Get file →
IQ4_XS2.2 GB 3.3 GB
Fits Get file →
IQ4_NL2.3 GB 3.4 GB
Fits Get file →
Q4_02.3 GB 3.4 GB
Fits Get file →
Q4_K_S2.3 GB 3.4 GB
Fits Get file →
Q4_K_M2.4 GB 3.5 GB
Fits Get file →
Q4_12.5 GB 3.6 GB
Fits Get file →
Q5_K_S2.8 GB 3.8 GB
Fits Get file →
Q5_K_M2.8 GB 3.9 GB
Fits Get file →
Q6_K3.2 GB 4.3 GB
Fits Get file →

What GPU do you need for Nanbeige4 3B Thinking Ties?

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 Q5_K_M (2.8 GB file, about 3.9 GB in use).
  • 6 GB VRAM: the best quant that fits is Q6_K (3.2 GB file, about 4.3 GB in use).

Which Nanbeige4 3B Thinking Ties quant should you choose?

Q4_K_M is the usual starting point for Nanbeige4 3B Thinking Ties: it balances file size and quality well. Here it is a 2.4 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

Architecturellama
Parameters3.93B
Layers32
Trained context65,536 tokens
KV cache (fp16)64 KB per token

Source

Quantized bymradermacher
FamilyNanbeige
Downloads (HF)352
Last updated2025-12-22

Frequently asked questions about Nanbeige4 3B Thinking Ties

How much VRAM does Nanbeige4 3B Thinking Ties need?

About 3.5 GB at Q4_K_M with an 8K context window. That is the 2.4 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 Nanbeige4 3B Thinking Ties on an 8 GB GPU?

Yes, with Q6_K: the 3.2 GB file needs about 4.3 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Nanbeige4 3B Thinking Ties GGUF?

It depends on the quant: file is 0.0 GB, IQ1_S is 1.1 GB, IQ1_M is 1.1 GB, IQ2_XXS is 1.3 GB, IQ2_XS is 1.3 GB, IQ2_S is 1.4 GB and 19 more.

What context length does Nanbeige4 3B Thinking Ties support?

The GGUF header lists a trained context length of 65,536 tokens (64K). The KV cache grows with the context you use: about 0.5 GB at 8K and 2.1 GB at 32K.

Where can I download Nanbeige4 3B Thinking Ties GGUF?

The files are on Hugging Face in the mradermacher/Nanbeige4-3B-Thinking-Ties-i1-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Other GGUFs of Nanbeige4-3B-Thinking-Ties

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Nanbeige models

All Nanbeige →

Other small models

All small models →