AS

asrv3

AsrvGGUF by CreativeHub008Updated 2026-09-06
Download on Hugging Face
Parameters938M
Context—
Layers28
Architectureqwen3-asr
Smallest quant1.8 GB
Quick answer

asrv3 needs about 3.3 GB of memory at F16 (a 1.9 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 4 quants, from 1.8 GB (F16) to 4.7 GB (F16).

asrv3 is a 938M-parameter Asrv model in GGUF format, quantized by CreativeHub008. The repository has 4 quant files, from 1.8 GB (F16) to 4.7 GB (F16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
F161.8 GB 3.3 GB
Fits Get file →
F161.9 GB 3.3 GB
Fits Get file →
Q8_03.2 GB 4.6 GB
Fits Get file →
F164.7 GB 6.1 GB
Fits Get file →

What GPU do you need for asrv3?

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 (1.9 GB file, about 3.3 GB in use).
  • 6 GB VRAM: the best quant that fits is Q8_0 (3.2 GB file, about 4.6 GB in use).
  • 8 GB VRAM: the best quant that fits is F16 (4.7 GB file, about 6.1 GB in use).

Which asrv3 quant should you choose?

F16 (1.9 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 F16 at 1.8 GB, with the quality trade-offs that come with fewer bits. The unquantized model. It gives original quality and needs the most memory, so it is mainly for conversion or reference.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen3-asr
Parameters938M
Layers28
KV cache (fp16)112 KB per token

Source

Quantized byCreativeHub008
FamilyAsrv
Downloads (HF)17
Last updated2026-09-06

Frequently asked questions about asrv3

How much VRAM does asrv3 need?

About 3.3 GB at F16 with an 8K context window. That is the 1.9 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 asrv3 on an 8 GB GPU?

Yes, with F16: the 4.7 GB file needs about 6.1 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of asrv3 GGUF?

It depends on the quant: F16 is 1.8 GB, F16 is 1.9 GB, Q8_0 is 3.2 GB, F16 is 4.7 GB.

Where can I download asrv3 GGUF?

The files are on Hugging Face in the CreativeHub008/asrv3 repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Similar models

Browse all →

More from CreativeHub008

All by CreativeHub008 →

Other tiny models

All tiny models →