QW

dhyield rp 14b v1 multi bilingual

QwenGGUF by dhyieldUpdated 2026-10-12
Download on Hugging Face
Parameters14.8B
Context32K
Layers48
Architectureqwen2
Smallest quant10.5 GB
Quick answer

dhyield rp 14b v1 multi bilingual needs about 12.6 GB of memory at Q5_K_M (a 10.5 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 2 quants, from 10.5 GB (Q5_K_M) to 29.5 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 6.4 GB.

14.8B parameter Qwen2.5 instruction model for Indonesian and English roleplay

dhyield rp 14b v1 multi bilingual is a 14.8B parameter Qwen2.5 model tuned for roleplay. It supports up to 32,768 context tokens and is trained from scratch by dhyield. The model follows system prompts and maintains character consistency.

Good at

  • Roleplay with consistent character names
  • Handling long context up to 32,768 tokens
  • Bilingual Indonesian and English dialogue

Limits

  • Requires more than 12.6GB VRAM for Q5_K_M quant
  • No vision or multimodal support
  • Apache‑2.0 license restricts commercial redistribution without attribution

Best for

  • Chatbots needing consistent roleplay
  • Long‑form bilingual conversations
  • Testing compliance with system prompts

Who it’s for. Developers building chat applications that require consistent roleplay in Indonesian and English. Researchers testing instruction‑tuned Qwen models on bilingual datasets.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q5_K_M10.5 GB 12.6 GB
Too big Get file →
BF1629.5 GB 31.7 GB
Too big Get file →

For 8‑GB VRAM, Q5_K_M is too large (12.6 GB estimate). BF16 requires 31.7 GB. If you have at least 16 GB VRAM, Q5_K_M is the most memory‑efficient option. For larger GPUs, BF16 offers higher precision.

What GPU do you need for dhyield rp 14b v1 multi bilingual?

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: no quant fits at an 8K context.
  • 12 GB VRAM: no quant fits at an 8K context.
  • 16 GB VRAM: the best quant that fits is Q5_K_M (10.5 GB file, about 12.6 GB in use).
  • 24 GB VRAM: the best quant that fits is Q5_K_M (10.5 GB file, about 12.6 GB in use).
  • 32 GB VRAM: the best quant that fits is BF16 (29.5 GB file, about 31.7 GB in use).

Which dhyield rp 14b v1 multi bilingual quant should you choose?

Q5_K_M (10.5 GB) is the middle option in this repository. Closer to the original model than 4-bit, for a moderate increase in size. A good pick when you have memory to spare.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen2
Parameters14.8B
Layers48
Trained context32,768 tokens
KV cache (fp16)192 KB per token

Source

Quantized bydhyield
FamilyQwen
Licenseapache-2.0
Downloads (HF)1,253
Last updated2026-10-12

Frequently asked questions about dhyield rp 14b v1 multi bilingual

How much VRAM does dhyield rp 14b v1 multi bilingual need?

About 12.6 GB at Q5_K_M with an 8K context window. That is the 10.5 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 dhyield rp 14b v1 multi bilingual on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 12.6 GB, so you would need a larger GPU or CPU offloading.

What is the file size of dhyield rp 14b v1 multi bilingual GGUF?

It depends on the quant: Q5_K_M is 10.5 GB, BF16 is 29.5 GB.

What context length does dhyield rp 14b v1 multi bilingual support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 1.6 GB at 8K and 6.4 GB at 32K.

Where can I download dhyield rp 14b v1 multi bilingual GGUF?

The files are on Hugging Face in the dhyield/dhyield-rp-14b-v1-multi-bilingual repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does dhyield rp 14b v1 multi bilingual 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?

No. The smallest quant, Q5_K_M, needs about 12.6 GB of VRAM at 8K context.

Does it support Indonesian and English?

Yes, the model is bilingual and designed for roleplay in both languages.

What license applies?

The model is released under Apache‑2.0, allowing free use with attribution.

Other GGUFs of Qwen2.5-14B-Instruct

Similar models

Browse all →

More Qwen models

All Qwen →

Other medium models

All medium models →