SA

SanGuoYanYi 6b

SanguoyanyiGGUF by RichardErkhovUpdated 2024-10-17
Download on Hugging Face
Parameters6.06B
Context4K
Layers32
Architecturellama
Smallest quant2.3 GB
Quick answer

SanGuoYanYi 6b needs about 4.7 GB of memory at Q4_K_M (a 3.7 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 22 quants, from 2.3 GB (Q2_K) to 6.4 GB (Q8_0).

SanGuoYanYi 6b – a 6.06B llama-based text‑style transfer model

SanGuoYanYi 6b is a 6.06B parameter llama model fine‑tuned for Chinese literary style transfer. It supports a 4096 token context window and is available in multiple GGUF quantizations. The model is released under a custom license.

Good at

  • Chinese literary style transfer
  • Text rewriting with classic novel tones
  • Fine‑grained style adaptation

Limits

  • No vision support
  • License is custom and not standard
  • Requires 8k context for full performance

Best for

  • Academic research on style transfer
  • Creative writing assistance
  • Educational tools for Chinese literature

Who it’s for. Researchers and developers needing a Chinese text‑style transfer model. The model is suitable for projects that require fine‑grained literary style adaptation and can run on systems with sufficient VRAM for the chosen quantization.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K2.3 GB 3.1 GB
Fits Get file →
IQ3_XS2.6 GB 3.4 GB
Fits Get file →
Q3_K_S2.7 GB 3.5 GB
Fits Get file →
IQ3_S2.7 GB 3.5 GB
Fits Get file →
IQ3_M2.8 GB 3.6 GB
Fits Get file →
Q3_K3.0 GB 3.8 GB
Fits Get file →
Q3_K_M3.0 GB 3.8 GB
Fits Get file →
Q3_K_L3.2 GB 4.0 GB
Fits Get file →
IQ4_XS3.3 GB 4.1 GB
Fits Get file →
Q4_03.5 GB 4.2 GB
Fits Get file →
Q4_K_S3.5 GB 4.3 GB
Fits Get file →
IQ4_NL3.5 GB 4.3 GB
Fits Get file →
Q4_K3.7 GB 4.4 GB
Fits Get file →
Q4_K_M3.7 GB 4.4 GB
Fits Get file →
Q4_13.8 GB 4.6 GB
Fits Get file →
Q5_04.2 GB 5.0 GB
Fits Get file →
Q5_K_S4.2 GB 5.0 GB
Fits Get file →
Q5_K4.3 GB 5.1 GB
Fits Get file →
Q5_K_M4.3 GB 5.1 GB
Fits Get file →
Q5_14.6 GB 5.3 GB
Fits Get file →
Q6_K5.0 GB 5.7 GB
Fits Get file →
Q8_06.4 GB 7.2 GB
Tight Get file →

For 8 GB VRAM, use Q4_K or Q4_K_M (file size 3.67 GB, estimated memory 4.7 GB). For 12 GB VRAM, Q5_K or Q5_K_M (file size 4.3 GB, estimated memory 5.3 GB). For 16 GB VRAM, Q6_K (file size 4.97 GB, estimated memory 6 GB).

What GPU do you need for SanGuoYanYi 6b?

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 (3.0 GB file, about 4.0 GB in use).
  • 6 GB VRAM: the best quant that fits is Q6_K (5.0 GB file, about 6.0 GB in use).
  • 8 GB VRAM: the best quant that fits is Q8_0 (6.4 GB file, about 7.5 GB in use).

Which SanGuoYanYi 6b quant should you choose?

Q4_K_M is the usual starting point for SanGuoYanYi 6b: it balances file size and quality well. Here it is a 3.7 GB file.

The Q8_0 file is 6.4 GB, about 1.8 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 Q2_K at 2.3 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters6.06B
Layers32
Trained context4,096 tokens
KV cache (fp16)64 KB per token

Source

Quantized byRichardErkhov
Licenseother
Downloads (HF)1,070
Last updated2024-10-17

Frequently asked questions about SanGuoYanYi 6b

How much VRAM does SanGuoYanYi 6b need?

About 4.7 GB at Q4_K_M with an 8K context window. That is the 3.7 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 SanGuoYanYi 6b on an 8 GB GPU?

Yes, with Q8_0: the 6.4 GB file needs about 7.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of SanGuoYanYi 6b GGUF?

It depends on the quant: Q2_K is 2.3 GB, IQ3_XS is 2.6 GB, Q3_K_S is 2.7 GB, IQ3_S is 2.7 GB, IQ3_M is 2.8 GB, Q3_K is 3.0 GB and 16 more.

What context length does SanGuoYanYi 6b support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 0.5 GB at 8K and 0.3 GB at 4K.

Where can I download SanGuoYanYi 6b GGUF?

The files are on Hugging Face in the RichardErkhov/stylellm_-_SanGuoYanYi-6b-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 SanGuoYanYi 6b 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.

Can I run SanGuoYanYi 6b on 8 GB VRAM?

Yes, use a Q4_K or Q4_K_M quantization. The estimated VRAM usage is approximately 4.7 GB at 8k context.

What context length does the model support?

The model was trained with a 4096 token context length and performs best with that size.

Does the model support vision tasks?

No, the model is text‑only and does not support vision inputs.

Similar models

Browse all →

More from RichardErkhov

All by RichardErkhov →

More Sanguoyanyi models

All Sanguoyanyi →

Other small models

All small models →