DR

Droplychee Moe v2

DroplycheeGGUF by mradermacherUpdated 2026-07-28
Download on Hugging Face
Parameters29.9B
Context198K
Layers47
Architecturedeepseek2
Smallest quant0.1 GB
Quick answer

Droplychee Moe v2 needs about 19.5 GB of memory at Q4_K_M (a 18.1 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 24 quants, from 0.1 GB to 24.6 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 3.4 GB.

Droplychee Moe v2 – a 29.9B parameter deepseek2 model fine‑tuned for reasoning and tools

Droplychee Moe v2 is a 29.9B parameter model based on deepseek2 architecture. It is a mixture of experts fine‑tuned from droplychee/droplychee-moe-v2. The model is licensed under apache-2.0 and supports reasoning and tool usage.

Good at

  • Reasoning
  • Tool usage
  • Mixture of experts

Limits

  • No vision support
  • Requires large VRAM for higher quants
  • Context limited to 202752 tokens

Best for

  • Chatbot development
  • Tool‑integrated assistants
  • Complex reasoning tasks

Who it’s for. Developers building advanced conversational agents who need reasoning and tool‑use capabilities. The model is suitable for users with sufficient GPU memory to run higher‑quality quants.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.1 GB 1.4 GB
Fits Get file →
IQ1_S6.2 GB 7.5 GB
Tight Get file →
IQ1_M6.9 GB 8.2 GB
Too big Get file →
IQ2_XXS8.0 GB 9.3 GB
Too big Get file →
IQ2_XS8.9 GB 10.2 GB
Too big Get file →
IQ2_S9.0 GB 10.4 GB
Too big Get file →
IQ2_M9.9 GB 11.2 GB
Too big Get file →
Q2_K_S10.2 GB 11.6 GB
Too big Get file →
Q2_K11.0 GB 12.4 GB
Too big Get file →
IQ3_XXS11.6 GB 13.0 GB
Too big Get file →
IQ3_XS12.3 GB 13.7 GB
Too big Get file →
IQ3_S13.0 GB 14.4 GB
Too big Get file →
Q3_K_S13.0 GB 14.4 GB
Too big Get file →
IQ3_M13.2 GB 14.5 GB
Too big Get file →
Q3_K_M14.4 GB 15.7 GB
Too big Get file →
Q3_K_L15.6 GB 16.9 GB
Too big Get file →
IQ4_XS16.0 GB 17.4 GB
Too big Get file →
Q4_017.0 GB 18.3 GB
Too big Get file →
Q4_K_S17.1 GB 18.4 GB
Too big Get file →
Q4_K_M18.1 GB 19.5 GB
Too big Get file →
Q4_118.8 GB 20.1 GB
Too big Get file →
Q5_K_S20.7 GB 22.0 GB
Too big Get file →
Q5_K_M21.3 GB 22.6 GB
Too big Get file →
Q6_K24.6 GB 26.0 GB
Too big Get file →

For 8 GB VRAM, use IQ1_S (file size 6.2 GB, estimated 7.5 GB memory at 8 k context). For 12 GB VRAM, IQ2_XXS (7.97 GB, 9.3 GB memory) is a good balance. For 16 GB VRAM, Q4_K_M (18.13 GB, 19.5 GB memory) provides higher quality.

What GPU do you need for Droplychee Moe v2?

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 the main file (0.1 GB file, about 1.4 GB in use).
  • 6 GB VRAM: the best quant that fits is the main file (0.1 GB file, about 1.4 GB in use).
  • 8 GB VRAM: the best quant that fits is IQ1_S (6.2 GB file, about 7.5 GB in use).
  • 12 GB VRAM: the best quant that fits is Q2_K_S (10.2 GB file, about 11.6 GB in use).
  • 16 GB VRAM: the best quant that fits is Q3_K_M (14.4 GB file, about 15.7 GB in use).
  • 24 GB VRAM: the best quant that fits is Q5_K_M (21.3 GB file, about 22.6 GB in use).
  • 32 GB VRAM: the best quant that fits is Q6_K (24.6 GB file, about 26.0 GB in use).

Which Droplychee Moe v2 quant should you choose?

Q4_K_M is the usual starting point for Droplychee Moe v2: it balances file size and quality well. Here it is a 18.1 GB file.

If memory is tight, the smallest file is the first one in the table at 0.1 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

Architecturedeepseek2
Parameters29.9B (approximate, mixture of experts)
Layers47
Trained context202,752 tokens
KV cache (fp16)100 KB per token

Source

Quantized bymradermacher
Licenseapache-2.0
Downloads (HF)579
Last updated2026-07-28

Frequently asked questions about Droplychee Moe v2

How much VRAM does Droplychee Moe v2 need?

About 19.5 GB at Q4_K_M with an 8K context window. That is the 18.1 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 Droplychee Moe v2 on an 8 GB GPU?

Yes, with IQ1_S: the 6.2 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 Droplychee Moe v2 GGUF?

It depends on the quant: file is 0.1 GB, IQ1_S is 6.2 GB, IQ1_M is 6.9 GB, IQ2_XXS is 8.0 GB, IQ2_XS is 8.9 GB, IQ2_S is 9.0 GB and 18 more.

What context length does Droplychee Moe v2 support?

The GGUF header lists a trained context length of 202,752 tokens (198K). The KV cache grows with the context you use: about 0.8 GB at 8K and 3.4 GB at 32K.

Where can I download Droplychee Moe v2 GGUF?

The files are on Hugging Face in the mradermacher/droplychee-moe-v2-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 Droplychee Moe v2 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 Droplychee Moe v2 on 8 GB VRAM?

Use the IQ1_S quant, which requires about 7.5 GB of VRAM at 8 k context. The base file is 6.2 GB.

Does this model support image input?

No, the model does not have vision capabilities.

What license applies to this model?

The model is released under the apache-2.0 license.

Other GGUFs of droplychee-moe-v2

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Droplychee models

All Droplychee →

Other medium models

All medium models →