GR

granite speech 4.1 2b nar

GraniteGGUF by cstrUpdated 2026-08-02
Download on Hugging Face
Parameters2.25B
Context—
Layers—
Architecturegranite_nle
Smallest quant1.6 GB
Quick answer

granite speech 4.1 2b nar needs about 3.3 GB of memory at Q4_K (a 2.5 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 4 quants, from 1.6 GB (Q4_K) to 5.8 GB (F16).

Granite Speech 4.1 2B NAR – fast, non‑autoregressive ASR

Granite Speech 4.1 2B NAR is a non‑autoregressive speech recognition model that edits a CTC hypothesis in a single forward pass. It achieves competitive accuracy with faster inference than autoregressive alternatives. The model supports English, French, German, Spanish, and Portuguese.

Good at

  • Fast inference for latency‑sensitive ASR
  • Non‑autoregressive editing architecture
  • Supports multiple European languages

Limits

  • No vision support
  • Requires flash_attention_2
  • No speaker or word‑timing output

Best for

  • Real‑time transcription in mobile apps
  • Batch processing of audio streams
  • Low‑latency voice assistants

Who it’s for. Developers building speech‑to‑text services that need quick turnaround and moderate accuracy. Researchers exploring non‑autoregressive ASR architectures may also find it useful.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K1.6 GB 2.3 GB
Fits Get file →
Q4_K2.5 GB 3.3 GB
Fits Get file →
Q4_K3.4 GB 4.3 GB
Fits Get file →
F165.8 GB 6.9 GB
Fits Get file →

For 8 GB VRAM, use the Q4_K 1.62 GB file (est. 2.3 GB memory at 8 k context). If 12 GB VRAM is available, the 2.53 GB Q4_K file (est. 3.3 GB) offers a larger model. The 5.76 GB F16 file requires 6.9 GB memory and is suitable only for higher‑end GPUs.

What GPU do you need for granite speech 4.1 2b nar?

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 Q4_K (2.5 GB file, about 3.3 GB in use).
  • 6 GB VRAM: the best quant that fits is Q4_K (3.4 GB file, about 4.3 GB in use).
  • 8 GB VRAM: the best quant that fits is F16 (5.8 GB file, about 6.9 GB in use).

Which granite speech 4.1 2b nar quant should you choose?

Q4_K (2.5 GB) is the middle option in this repository. The usual sweet spot between file size and quality, and the quant most people start with.

If memory is tight, the smallest file is Q4_K at 1.6 GB, with the quality trade-offs that come with fewer bits. 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

Architecturegranite_nle
Parameters2.25B

Source

Quantized bycstr
FamilyGranite
Licenseapache-2.0
Downloads (HF)1,369
Last updated2026-08-02

Frequently asked questions about granite speech 4.1 2b nar

How much VRAM does granite speech 4.1 2b nar need?

About 3.3 GB at Q4_K with an 8K context window. That is the 2.5 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 granite speech 4.1 2b nar on an 8 GB GPU?

Yes, with F16: the 5.8 GB file needs about 6.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of granite speech 4.1 2b nar GGUF?

It depends on the quant: Q4_K is 1.6 GB, Q4_K is 2.5 GB, Q4_K is 3.4 GB, F16 is 5.8 GB.

Where can I download granite speech 4.1 2b nar GGUF?

The files are on Hugging Face in the cstr/granite-speech-4.1-2b-nar-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 granite speech 4.1 2b nar 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 1.62 GB Q4_K file uses about 2.3 GB memory at 8 k context, fitting within 8 GB VRAM.

Does the model support speaker attribution?

No, speaker labels and word‑timing are not included in this NAR variant.

What license applies to this model?

The model is released under the Apache 2.0 license.

Other GGUFs of granite-speech-4.1-2b-nar

Similar models

Browse all →

More from cstr

All by cstr →

More Granite models

All Granite →

Other tiny models

All tiny models →