FI

FireRedLID

FireredlidGGUF by cstrUpdated 2026-08-02
Download on Hugging Face
Parameters887M
Context—
Layers—
Architecturefirered-lid
Smallest quant0.4 GB
Quick answer

FireRedLID needs about 1.6 GB of memory at Q8_0 (a 1.0 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 5 quants, from 0.4 GB (Q2_K) to 1.8 GB.

FireRedLID – Spoken Language Identification model in GGUF format

FireRedLID is a spoken language identification module of the FireRedASR2S system. It supports over 100 languages and 20+ Chinese dialects, achieving 97.18% accuracy on the FLEURS benchmark. The model is released under the Apache‑2.0 license.

Good at

  • High‑accuracy LID for 100+ languages
  • Compact GGUF quantisations
  • Integration with FireRedASR2S

Limits

  • No vision support
  • Requires 8k context for memory estimates
  • No training data provided

Best for

  • Speech‑to‑text pipelines needing language detection
  • Multilingual voice assistants
  • Batch language tagging of audio files

Who it’s for. Developers building industrial‑grade ASR systems that need reliable language identification. The model is suitable for applications requiring a lightweight, quantisable LID component.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K0.4 GB 0.9 GB
Fits Get file →
Q4_K0.6 GB 1.1 GB
Fits Get file →
Q8_01.0 GB 1.6 GB
Fits Get file →
F161.8 GB 2.5 GB
Fits Get file →
—1.8 GB 2.5 GB
Fits Get file →

For 8 GB VRAM, Q2_K (0.37 GB, 0.9 GB memory at 8k context) is ideal. Q4_K (0.57 GB, 1.1 GB memory) fits 12 GB VRAM. For higher precision, Q8_0 (1 GB, 1.6 GB memory) or F16 (1.81 GB, 2.5 GB memory) can be used on GPUs with 16 GB or more.

What GPU do you need for FireRedLID?

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 (1.8 GB file, about 2.5 GB in use).

Which FireRedLID quant should you choose?

Q8_0 (1.0 GB) is the middle option in this repository. Close to lossless. It costs roughly twice the memory of a 4-bit file, so it suits cases where you have plenty of VRAM.

If memory is tight, the smallest file is Q2_K at 0.4 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

Architecturefirered-lid
Parameters887M

Source

Quantized bycstr
Licenseapache-2.0
Downloads (HF)1,194
Last updated2026-08-02

Frequently asked questions about FireRedLID

How much VRAM does FireRedLID need?

About 1.6 GB at Q8_0 with an 8K context window. That is the 1.0 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 FireRedLID on an 8 GB GPU?

Yes, with the smaller files: the 1.8 GB file needs about 2.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of FireRedLID GGUF?

It depends on the quant: Q2_K is 0.4 GB, Q4_K is 0.6 GB, Q8_0 is 1.0 GB, F16 is 1.8 GB, file is 1.8 GB.

Where can I download FireRedLID GGUF?

The files are on Hugging Face in the cstr/firered-lid-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 FireRedLID 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 FireRedLID on a GPU with 8 GB VRAM?

Yes, the Q2_K quantisation uses 0.9 GB memory at 8k context, fitting comfortably in 8 GB VRAM.

How many languages does FireRedLID support?

It supports 100+ languages and 20+ Chinese dialects/accents.

What license applies to FireRedLID?

The model is released under the Apache‑2.0 license.

Similar models

Browse all →

More from cstr

All by cstr →

Other tiny models

All tiny models →