DO

Dolphin 2.7 Yayi2 30b

DolphinGGUF by mradermacherUpdated 2025-07-14
Download on Hugging Face
Parameters30.4B
Context8K
Layers64
Architecturellama
Smallest quant6.7 GB
Quick answer

Dolphin 2.7 Yayi2 30b needs about 19.0 GB of memory at Q4_K_M (a 18.2 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 23 quants, from 6.7 GB (IQ1_S) to 24.9 GB (Q6_K).

Dolphin 2.7 Yayi2 30b is a 30.4B-parameter Dolphin model in GGUF format, quantized by mradermacher. Its trained context length is 8K tokens. The repository has 23 quant files, from 6.7 GB (IQ1_S) to 24.9 GB (Q6_K).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S6.7 GB 7.4 GB
Tight Get file →
IQ1_M7.2 GB 8.0 GB
Tight Get file →
IQ2_XXS8.2 GB 9.0 GB
Too big Get file →
IQ2_XS9.1 GB 9.8 GB
Too big Get file →
IQ2_S9.7 GB 10.5 GB
Too big Get file →
IQ2_M10.5 GB 11.2 GB
Too big Get file →
Q2_K_S10.5 GB 11.2 GB
Too big Get file →
Q2_K11.4 GB 12.1 GB
Too big Get file →
IQ3_XXS11.8 GB 12.5 GB
Too big Get file →
IQ3_XS12.6 GB 13.4 GB
Too big Get file →
Q3_K_S13.3 GB 14.0 GB
Too big Get file →
IQ3_S13.3 GB 14.0 GB
Too big Get file →
IQ3_M13.9 GB 14.6 GB
Too big Get file →
Q3_K_M14.8 GB 15.5 GB
Too big Get file →
Q3_K_L16.1 GB 16.8 GB
Too big Get file →
IQ4_XS16.3 GB 17.1 GB
Too big Get file →
Q4_017.3 GB 18.1 GB
Too big Get file →
Q4_K_S17.4 GB 18.1 GB
Too big Get file →
Q4_K_M18.2 GB 19.0 GB
Too big Get file →
Q4_119.1 GB 19.9 GB
Too big Get file →
Q5_K_S21.0 GB 21.7 GB
Too big Get file →
Q5_K_M21.5 GB 22.2 GB
Too big Get file →
Q6_K24.9 GB 25.7 GB
Too big Get file →

What GPU do you need for Dolphin 2.7 Yayi2 30b?

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 IQ1_M (7.2 GB file, about 8.0 GB in use).
  • 12 GB VRAM: the best quant that fits is Q2_K_S (10.5 GB file, about 11.2 GB in use).
  • 16 GB VRAM: the best quant that fits is Q3_K_M (14.8 GB file, about 15.5 GB in use).
  • 24 GB VRAM: the best quant that fits is Q5_K_M (21.5 GB file, about 22.2 GB in use).
  • 32 GB VRAM: the best quant that fits is Q6_K (24.9 GB file, about 25.7 GB in use).

Which Dolphin 2.7 Yayi2 30b quant should you choose?

Q4_K_M is the usual starting point for Dolphin 2.7 Yayi2 30b: it balances file size and quality well. Here it is a 18.2 GB file.

If memory is tight, the smallest file is IQ1_S at 6.7 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
Parameters30.4B
Layers64
Trained context8,192 tokens
KV cache (fp16)28 KB per token

Source

Quantized bymradermacher
FamilyDolphin
Licenseapache-2.0
Downloads (HF)523
Last updated2025-07-14

Frequently asked questions about Dolphin 2.7 Yayi2 30b

How much VRAM does Dolphin 2.7 Yayi2 30b need?

About 19.0 GB at Q4_K_M with an 8K context window. That is the 18.2 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 Dolphin 2.7 Yayi2 30b on an 8 GB GPU?

Yes, with IQ1_M: the 7.2 GB file needs about 8.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Dolphin 2.7 Yayi2 30b GGUF?

It depends on the quant: IQ1_S is 6.7 GB, IQ1_M is 7.2 GB, IQ2_XXS is 8.2 GB, IQ2_XS is 9.1 GB, IQ2_S is 9.7 GB, IQ2_M is 10.5 GB and 17 more.

What context length does Dolphin 2.7 Yayi2 30b support?

The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 0.2 GB at 8K and 0.2 GB at 8K.

Where can I download Dolphin 2.7 Yayi2 30b GGUF?

The files are on Hugging Face in the mradermacher/dolphin-2.7-yayi2-30b-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 Dolphin 2.7 Yayi2 30b 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 dolphin-2.7-yayi2-30b

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Dolphin models

All Dolphin →

Other medium models

All medium models →