AU

Audiogemma 3N Finetune

AudiogemmaGGUF by mradermacherUpdated 2026-01-21
Download on Hugging Face
Parameters6.87B
Context32K
Layers35
Architecturegemma3n
Smallest quant0.0 GB
Quick answer

Audiogemma 3N Finetune needs about 5.3 GB of memory at Q4_K_M (a 4.2 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 17 quants, from 0.0 GB to 5.7 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 2.3 GB.

Audiogemma 3N Finetune – audio transcription model

Audiogemma 3N Finetune is a 6.87B parameter model fine‑tuned for audio transcription. It accepts text, images, video, and audio inputs and outputs text. The model was trained on over 140 spoken languages.

Good at

  • Audio transcription
  • Multimodal input handling
  • Text generation

Limits

  • No vision support in this GGUF release
  • Requires 32K token context
  • Apache‑2.0 license

Best for

  • Transcribing podcasts
  • Generating subtitles
  • Audio‑to‑text pipelines

Who it’s for. Developers building audio transcription services or integrating multimodal LLMs into applications. The model is suitable for low‑resource devices due to its efficient parameter management.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 1.1 GB
Fits Get file →
Q2_K2.8 GB 3.8 GB
Fits Get file →
IQ3_XS3.2 GB 4.3 GB
Fits Get file →
Q3_K_S3.3 GB 4.3 GB
Fits Get file →
IQ3_S3.3 GB 4.3 GB
Fits Get file →
IQ3_M3.3 GB 4.4 GB
Fits Get file →
Q3_K_M3.4 GB 4.5 GB
Fits Get file →
Q3_K_L3.6 GB 4.7 GB
Fits Get file →
IQ4_XS3.9 GB 5.0 GB
Fits Get file →
IQ4_NL4.1 GB 5.2 GB
Fits Get file →
Q4_04.1 GB 5.2 GB
Fits Get file →
Q4_K_S4.1 GB 5.2 GB
Fits Get file →
Q4_K_M4.2 GB 5.3 GB
Fits Get file →
Q4_14.5 GB 5.6 GB
Fits Get file →
Q5_K_S4.9 GB 6.0 GB
Fits Get file →
Q5_K_M5.0 GB 6.0 GB
Fits Get file →
Q6_K5.7 GB 6.8 GB
Fits Get file →

For 8 GB VRAM, use Q4_K_M (4.24 GB file, 5.3 GB memory at 8K context). For 12 GB VRAM, Q5_K_M (4.95 GB file, 6 GB memory) offers higher quality. If memory is limited, Q2_K (2.76 GB file, 3.8 GB memory) is a lightweight option.

What GPU do you need for Audiogemma 3N Finetune?

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 Q2_K (2.8 GB file, about 3.8 GB in use).
  • 6 GB VRAM: the best quant that fits is Q5_K_M (5.0 GB file, about 6.0 GB in use).
  • 8 GB VRAM: the best quant that fits is Q6_K (5.7 GB file, about 6.8 GB in use).

Which Audiogemma 3N Finetune quant should you choose?

Q4_K_M is the usual starting point for Audiogemma 3N Finetune: it balances file size and quality well. Here it is a 4.2 GB file.

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

Architecturegemma3n
Parameters6.87B
Layers35
Trained context32,768 tokens
KV cache (fp16)70 KB per token

Source

Quantized bymradermacher
Licenseapache-2.0
Downloads (HF)610
Last updated2026-01-21

Frequently asked questions about Audiogemma 3N Finetune

How much VRAM does Audiogemma 3N Finetune need?

About 5.3 GB at Q4_K_M with an 8K context window. That is the 4.2 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 Audiogemma 3N Finetune on an 8 GB GPU?

Yes, with Q6_K: the 5.7 GB file needs about 6.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Audiogemma 3N Finetune GGUF?

It depends on the quant: file is 0.0 GB, Q2_K is 2.8 GB, IQ3_XS is 3.2 GB, Q3_K_S is 3.3 GB, IQ3_S is 3.3 GB, IQ3_M is 3.3 GB and 11 more.

What context length does Audiogemma 3N Finetune support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 0.6 GB at 8K and 2.3 GB at 32K.

Where can I download Audiogemma 3N Finetune GGUF?

The files are on Hugging Face in the mradermacher/Audiogemma-3N-finetune-i1-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 Audiogemma 3N Finetune 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 Audiogemma 3N Finetune on 8 GB VRAM?

Yes, the Q4_K_M quant requires about 5.3 GB of VRAM at 8K context, which fits within an 8 GB GPU.

Does this model support image input?

The GGUF release focuses on audio transcription; image support is not included in the provided files.

What license applies to this model?

The model is released under the Apache‑2.0 license.

Other GGUFs of Audiogemma-3N-finetune

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Audiogemma models

All Audiogemma →

Other small models

All small models →