HU

hubert large ls960 ft

HubertGGUF by cstrUpdated 2026-08-02
Download on Hugging Face
Parameters315M
Context—
Layers—
Architecturewav2vec2
Smallest quant0.2 GB
Quick answer

hubert large ls960 ft needs about 0.7 GB of memory at Q4_K (a 0.2 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 2 quants, from 0.2 GB (Q4_K) to 0.7 GB (F16).

Hubert Large fine‑tuned on 960h Librispeech for speech recognition

Hubert Large fine‑tuned on 960h Librispeech at 16kHz. The model is a wav2vec2‑style CNN with a 24‑layer transformer and a CTC head. It is licensed under Apache‑2.0 and supports English speech only.

Good at

  • Speech recognition on 16kHz audio
  • Fine‑tuned for Librispeech 960h
  • CTC‑based transcription

Limits

  • No vision support
  • English only
  • Requires 16kHz audio

Best for

  • Transcribing spoken lectures
  • Generating subtitles for podcasts
  • Voice‑to‑text in English

Who it’s for. Developers building speech‑to‑text pipelines who need a pre‑trained, fine‑tuned model for English. Researchers working on ASR benchmarks may also use it.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K0.2 GB 0.7 GB
Fits Get file →
F160.7 GB 1.2 GB
Fits Get file →

For 8 GB VRAM, the Q4_K quant (0.22 GB) uses about 0.7 GB memory at 8 k context, fitting comfortably. If higher precision is needed and 8 GB is available, the F16 quant (0.66 GB) uses about 1.2 GB memory and offers better accuracy.

What GPU do you need for hubert large ls960 ft?

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 F16 (0.7 GB file, about 1.2 GB in use).

Which hubert large ls960 ft quant should you choose?

Q4_K (0.2 GB) is the middle option in this repository. The usual sweet spot between file size and quality, and the quant most people start with.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturewav2vec2
Parameters315M

Source

Quantized bycstr
FamilyHubert
Licenseapache-2.0
Downloads (HF)1,688
Last updated2026-08-02

Frequently asked questions about hubert large ls960 ft

How much VRAM does hubert large ls960 ft need?

About 0.7 GB at Q4_K with an 8K context window. That is the 0.2 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 hubert large ls960 ft on an 8 GB GPU?

Yes, with F16: the 0.7 GB file needs about 1.2 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of hubert large ls960 ft GGUF?

It depends on the quant: Q4_K is 0.2 GB, F16 is 0.7 GB.

Where can I download hubert large ls960 ft GGUF?

The files are on Hugging Face in the cstr/hubert-large-ls960-ft-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 hubert large ls960 ft 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 this model on 8 GB VRAM?

Yes, the Q4_K quant uses about 0.7 GB memory at 8 k context, fitting within 8 GB VRAM.

Does this model support languages other than English?

No, the model is fine‑tuned for English only.

What license does this model use?

Apache‑2.0, the same as the upstream Facebook model.

Other GGUFs of hubert-large-ls960-ft

Similar models

Browse all →

More from cstr

All by cstr →

More Hubert models

All Hubert →

Other tiny models

All tiny models →