ME

melotts en v2

MelottsGGUF by cstrUpdated 2026-08-02
Download on Hugging Face
Parameters95M
Context—
Layers—
Architecturebert
Smallest quant0.1 GB
Quick answer

melotts en v2 needs about 0.6 GB of memory at F16 (a 0.1 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 4 quants, from 0.1 GB to 0.2 GB.

Melotts English V2 – 94.7M‑parameter BERT model in GGUF format

Melotts English V2 is a 94.7‑billion‑parameter BERT architecture converted to GGUF by cstr. The model is released under the MIT license and supports English language processing. It is available in several quantisations for different memory budgets.

Good at

  • English text understanding
  • Lightweight inference
  • Low‑memory deployment

Limits

  • No vision or audio capabilities
  • Requires at least 0.6 GB VRAM for 8 k context
  • No training or fine‑tuning support

Best for

  • Chatbot back‑end
  • Text classification tasks
  • Embedding generation

Who it’s for. Developers and researchers needing a compact BERT‑style model for English text tasks. The model is suitable for edge deployments where memory is limited.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.1 GB 0.6 GB
Fits Get file →
F160.1 GB 0.6 GB
Fits Get file →
Q8_00.1 GB 0.6 GB
Fits Get file →
—0.2 GB 0.8 GB
Fits Get file →

For 8 GB VRAM, the F16 or Q8_0 quantisations (0.1 GB file, 0.6 GB memory) are recommended. If 4 GB VRAM is available, the 0.05 GB unknown quantisation can be used, though memory usage remains 0.6 GB. The 0.24 GB unknown quantisation requires 0.8 GB memory and is best for higher‑capacity systems.

What GPU do you need for melotts en v2?

These figures add the file size, an fp16 KV cache at an 8K context window 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 (0.2 GB file, about 0.8 GB in use).

Which melotts en v2 quant should you choose?

F16 (0.1 GB) is the middle option in this repository. The unquantized model. It gives original quality and needs the most memory, so it is mainly for conversion or reference.

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

Architecturebert
Parameters95M

Source

Quantized bycstr
FamilyMelotts
Licensemit
Downloads (HF)922
Last updated2026-08-02

Frequently asked questions about melotts en v2

How much VRAM does melotts en v2 need?

About 0.6 GB at F16 with an 8K context window. That is the 0.1 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 melotts en v2 on an 8 GB GPU?

Yes, with the smaller files: the 0.2 GB file needs about 0.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of melotts en v2 GGUF?

It depends on the quant: file is 0.1 GB, F16 is 0.1 GB, Q8_0 is 0.1 GB, file is 0.2 GB.

Where can I download melotts en v2 GGUF?

The files are on Hugging Face in the cstr/melotts-en-v2-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 melotts en v2 use?

Hugging Face lists the license as mit. 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 Melotts English V2 on 8 GB VRAM?

Yes, the F16 or Q8_0 quantisations use 0.6 GB memory at 8 k context, fitting comfortably in 8 GB VRAM.

Does the model support other languages?

No, the model is designed for English only.

Is the model suitable for real‑time inference?

Yes, the low memory footprint and small parameter count make it suitable for real‑time applications.

Similar models

Browse all →

More from cstr

All by cstr →

More Melotts models

All Melotts →

Other tiny models

All tiny models →