NE

KO VoicePersona E4B

NemotronGGUF by ThakiCloudUpdated 2026-10-27
Download on Hugging Face
Parameters7.52B
Context64K
Layers42
Architecturegemma4
Smallest quant5.3 GB
Quick answer

KO VoicePersona E4B needs about 7.2 GB of memory at Q4_K_M (a 5.3 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 3 quants, from 5.3 GB (Q4_K_M) to 8.0 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 5.6 GB.

KO VoicePersona E4B – Korean voice‑assistant persona model

KO VoicePersona E4B is a 7.52 billion‑parameter language model fine‑tuned for Korean spoken personas. It generates short, TTS‑friendly replies and can call tools. The model is based on NVIDIA Nemotron‑3.5‑Bolt‑E4B.

Good at

  • Korean persona generation
  • Tool calling
  • Short TTS‑friendly replies

Limits

  • No speech synthesis or recognition
  • No vision support
  • Requires pre‑transcribed Korean text

Best for

  • Voice assistant prototypes
  • Embedded Korean AI agents
  • Tool‑enabled dialogue systems

Who it’s for. Developers building Korean voice assistants or embedded AI agents that need persona‑aware dialogue. The model is suitable for local deployment on GPUs with limited VRAM.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M5.3 GB 7.2 GB
Tight Get file →
Q4_K_M6.2 GB 8.1 GB
Too big Get file →
Q8_08.0 GB 9.9 GB
Too big Get file →

For 8 GB VRAM use the Q4_K_M 5.34 GB file, which needs about 7.2 GB memory at 8 k context. If more memory is available, the 6.18 GB Q4_K_M file uses 8.1 GB. The 8.03 GB Q8_0 file requires about 9.9 GB memory.

What GPU do you need for KO VoicePersona E4B?

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 Q4_K_M (5.3 GB file, about 7.2 GB in use).
  • 12 GB VRAM: the best quant that fits is Q8_0 (8.0 GB file, about 9.9 GB in use).

Which KO VoicePersona E4B quant should you choose?

Q4_K_M is the usual starting point for KO VoicePersona E4B: it balances file size and quality well. Here it is a 5.3 GB file.

The Q8_0 file is 8.0 GB, about 1.5 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.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturegemma4
Parameters7.52B
Layers42
Trained context65,536 tokens
KV cache (fp16)168 KB per token

Source

Quantized byThakiCloud
FamilyNemotron
Licenseother
Downloads (HF)726
Last updated2026-10-27

Frequently asked questions about KO VoicePersona E4B

How much VRAM does KO VoicePersona E4B need?

About 7.2 GB at Q4_K_M with an 8K context window. That is the 5.3 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 KO VoicePersona E4B on an 8 GB GPU?

Yes, with Q4_K_M: the 5.3 GB file needs about 7.2 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of KO VoicePersona E4B GGUF?

It depends on the quant: Q4_K_M is 5.3 GB, Q4_K_M is 6.2 GB, Q8_0 is 8.0 GB.

What context length does KO VoicePersona E4B support?

The GGUF header lists a trained context length of 65,536 tokens (64K). The KV cache grows with the context you use: about 1.4 GB at 8K and 5.6 GB at 32K.

Where can I download KO VoicePersona E4B GGUF?

The files are on Hugging Face in the ThakiCloud/KO-VoicePersona-E4B repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does KO VoicePersona E4B 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 KO VoicePersona E4B on 8 GB VRAM?

Yes, the 5.34 GB Q4_K_M quantized file fits 8 GB VRAM and needs about 7.2 GB memory at 8 k context.

Does this model support vision or speech?

No. It is a language model that expects pre‑transcribed Korean text and does not perform speech recognition or synthesis.

Is the model free for commercial use?

The model is released for commercial or non‑commercial use under the provided license.

Other GGUFs of NVIDIA-Nemotron-3.5-Bolt-E4B-BF16

Similar models

Browse all →

More from ThakiCloud

All by ThakiCloud →

More Nemotron models

All Nemotron →

Other small models

All small models →