MA

maya1

MayaGGUF by mradermacherUpdated 2026-10-25
Download on Hugging Face
Parameters3.3B
Context128K
Layers28
Architecturellama
Smallest quant1.4 GB
Quick answer

maya1 needs about 3.5 GB of memory at Q4_K_M (a 2.1 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 12 quants, from 1.4 GB (Q2_K) to 6.6 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 3.8 GB.

Maya-1: Open-weight text-to-speech model with natural-language voice control

Maya-1 is a 3.3‑billion parameter text‑to‑speech model that generates acoustic tokens from text and a voice description. It supports inline expressive markers and produces 24 kHz waveforms. The model is released under apache‑2.0.

Good at

  • Voice description via natural language
  • Inline expressive control
  • Acoustic‑token generation

Limits

  • No vision support
  • Requires 131072 context tokens
  • Large VRAM for higher quants

Best for

  • Custom voice synthesis
  • Narration with style control
  • Audio content creation

Who it’s for. Developers building voice assistants or media tools that need flexible voice styles. The model is open‑weight and can be fine‑tuned or used directly with llama.cpp.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K1.4 GB 2.9 GB
Fits Get file →
Q3_K_S1.6 GB 3.1 GB
Fits Get file →
Q3_K_M1.8 GB 3.2 GB
Fits Get file →
Q3_K_L1.9 GB 3.3 GB
Fits Get file →
IQ4_XS1.9 GB 3.4 GB
Fits Get file →
Q4_K_S2.0 GB 3.4 GB
Fits Get file →
Q4_K_M2.1 GB 3.5 GB
Fits Get file →
Q5_K_S2.3 GB 3.8 GB
Fits Get file →
Q5_K_M2.4 GB 3.8 GB
Fits Get file →
Q6_K2.7 GB 4.2 GB
Fits Get file →
Q8_03.5 GB 5.0 GB
Fits Get file →
F166.6 GB 8.1 GB
Too big Get file →

For 8 GB VRAM, use Q4_K_M (file size 2.09 GB, memory 3.5 GB). For 12 GB VRAM, Q5_K_M (2.4 GB, 3.8 GB) or Q6_K (2.72 GB, 4.2 GB). Higher quants like Q8_0 (3.52 GB, 5 GB) need 16 GB or more.

What GPU do you need for maya1?

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 Q5_K_M (2.4 GB file, about 3.8 GB in use).
  • 6 GB VRAM: the best quant that fits is Q8_0 (3.5 GB file, about 5.0 GB in use).
  • 8 GB VRAM: the best quant that fits is Q8_0 (3.5 GB file, about 5.0 GB in use).
  • 12 GB VRAM: the best quant that fits is F16 (6.6 GB file, about 8.1 GB in use).

Which maya1 quant should you choose?

Q4_K_M is the usual starting point for maya1: it balances file size and quality well. Here it is a 2.1 GB file.

The Q8_0 file is 3.5 GB, about 1.7 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.

If memory is tight, the smallest file is Q2_K at 1.4 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters3.3B
Layers28
Trained context131,072 tokens
KV cache (fp16)112 KB per token

Source

Quantized bymradermacher
FamilyMaya
Licenseapache-2.0
Downloads (HF)1,519
Last updated2026-10-25

Frequently asked questions about maya1

How much VRAM does maya1 need?

About 3.5 GB at Q4_K_M with an 8K context window. That is the 2.1 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 maya1 on an 8 GB GPU?

Yes, with Q8_0: the 3.5 GB file needs about 5.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of maya1 GGUF?

It depends on the quant: Q2_K is 1.4 GB, Q3_K_S is 1.6 GB, Q3_K_M is 1.8 GB, Q3_K_L is 1.9 GB, IQ4_XS is 1.9 GB, Q4_K_S is 2.0 GB and 6 more.

What context length does maya1 support?

The GGUF header lists a trained context length of 131,072 tokens (128K). 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 maya1 GGUF?

The files are on Hugging Face in the mradermacher/maya1-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 maya1 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 Maya-1 on 8 GB VRAM?

Yes, using Q4_K_M or Q4_K_S which require about 3.4 GB of VRAM at 8 k context.

Does Maya-1 support image input?

No, the model only processes text and voice descriptions.

Other GGUFs of maya1

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Maya models

All Maya →

Other tiny models

All tiny models →