MO

MOSS-TTS-PNY tokenizer

MossGGUF by ZDisketUpdated 2026-07-03
Download on Hugging Face
Parameters32M
Context40K
Layers28
Architectureqwen2
Smallest quant0.0 GB
Quick answer

MOSS-TTS-PNY tokenizer needs about 3.0 GB of memory at F16 (a 1.6 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 7 quants, from 0.0 GB to 6.6 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 3.8 GB.

MOSS-TTS-PNY tokenizer is a 32M-parameter Moss model in GGUF format, quantized by ZDisket. Its trained context length is 40K tokens. The repository has 7 quant files, from 0.0 GB to 6.6 GB (F16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 1.4 GB
Fits Get file →
F160.1 GB 1.5 GB
Fits Get file →
Q8_00.9 GB 2.3 GB
Fits Get file →
F161.6 GB 3.0 GB
Fits Get file →
Q6_K4.7 GB 6.1 GB
Fits Get file →
Q8_05.1 GB 6.5 GB
Fits Get file →
F166.6 GB 8.0 GB
Too big Get file →

What GPU do you need for MOSS-TTS-PNY tokenizer?

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 F16 (1.6 GB file, about 3.0 GB in use).
  • 6 GB VRAM: the best quant that fits is F16 (1.6 GB file, about 3.0 GB in use).
  • 8 GB VRAM: the best quant that fits is F16 (6.6 GB file, about 8.0 GB in use).

Which MOSS-TTS-PNY tokenizer quant should you choose?

F16 (1.6 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 0.0 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

Architectureqwen2
Parameters32M
Layers28
Trained context40,960 tokens
KV cache (fp16)112 KB per token

Source

Quantized byZDisket
FamilyMoss
Licenseother
Downloads (HF)355
Last updated2026-07-03

Frequently asked questions about MOSS-TTS-PNY tokenizer

How much VRAM does MOSS-TTS-PNY tokenizer need?

About 3.0 GB at F16 with an 8K context window. That is the 1.6 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 MOSS-TTS-PNY tokenizer on an 8 GB GPU?

Yes, with F16: the 6.6 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 MOSS-TTS-PNY tokenizer GGUF?

It depends on the quant: file is 0.0 GB, F16 is 0.1 GB, Q8_0 is 0.9 GB, F16 is 1.6 GB, Q6_K is 4.7 GB, Q8_0 is 5.1 GB and 1 more.

What context length does MOSS-TTS-PNY tokenizer support?

The GGUF header lists a trained context length of 40,960 tokens (40K). The KV cache grows with the context you use: about 0.9 GB at 8K and 3.8 GB at 32K.

Where can I download MOSS-TTS-PNY tokenizer GGUF?

The files are on Hugging Face in the ZDisket/MOSS-TTS-PNY-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 MOSS-TTS-PNY tokenizer 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.

Similar models

Browse all →

More Moss models

All Moss →

Other tiny models

All tiny models →