GR

Granite Speech 5.0 2b

GraniteGGUF by mradermacherUpdated 2026-10-22
Download on Hugging Face
Parameters1.84B
Context16K
Layers40
Architecturegranite
Smallest quant0.0 GB
Quick answer

Granite Speech 5.0 2b needs about 2.3 GB of memory at Q4_K_M (a 1.1 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 25 quants, from 0.0 GB to 1.5 GB (Q6_K).

Granite Speech 5.0 2B – compact multilingual ASR and AST model

Granite Speech 5.0 2B is a 1.84 billion‑parameter speech‑language model. It supports automatic speech recognition and bidirectional speech translation for English, French, German, Spanish, Portuguese and Japanese. The model is trained on 390,000 hours of audio and offers improved transcription accuracy and keyword‑biasing.

Good at

  • Multilingual ASR
  • Bidirectional speech translation
  • Keyword‑biased ASR

Limits

  • No vision support
  • Requires 8 k context for estimates
  • Apache‑2.0 license

Best for

  • Embedded ASR devices
  • Low‑latency translation apps
  • Keyword‑driven voice assistants

Who it’s for. Developers building speech‑enabled applications that need multilingual support and robust performance in noisy environments. The model is suitable for edge devices with limited GPU memory.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 1.2 GB
Fits Get file →
IQ1_S0.5 GB 1.7 GB
Fits Get file →
IQ1_M0.6 GB 1.7 GB
Fits Get file →
IQ2_XXS0.6 GB 1.8 GB
Fits Get file →
IQ2_XS0.6 GB 1.8 GB
Fits Get file →
IQ2_S0.7 GB 1.9 GB
Fits Get file →
IQ2_M0.7 GB 1.9 GB
Fits Get file →
Q2_K_S0.7 GB 1.9 GB
Fits Get file →
Q2_K0.8 GB 1.9 GB
Fits Get file →
IQ3_XXS0.8 GB 2.0 GB
Fits Get file →
IQ3_XS0.8 GB 2.0 GB
Fits Get file →
Q3_K_S0.9 GB 2.0 GB
Fits Get file →
IQ3_S0.9 GB 2.1 GB
Fits Get file →
IQ3_M0.9 GB 2.1 GB
Fits Get file →
Q3_K_M0.9 GB 2.1 GB
Fits Get file →
Q3_K_L1.0 GB 2.2 GB
Fits Get file →
IQ4_XS1.0 GB 2.2 GB
Fits Get file →
Q4_01.1 GB 2.3 GB
Fits Get file →
IQ4_NL1.1 GB 2.3 GB
Fits Get file →
Q4_K_S1.1 GB 2.3 GB
Fits Get file →
Q4_K_M1.1 GB 2.3 GB
Fits Get file →
Q4_11.2 GB 2.4 GB
Fits Get file →
Q5_K_S1.3 GB 2.5 GB
Fits Get file →
Q5_K_M1.3 GB 2.5 GB
Fits Get file →
Q6_K1.5 GB 2.7 GB
Fits Get file →

For 8 GB VRAM, use Q4_0 (file size 1.09 GB, estimated 2.3 GB memory). For 4 GB VRAM, use IQ1_S (0.52 GB, 1.7 GB memory). For 2 GB VRAM, use IQ1_M (0.55 GB, 1.7 GB memory).

What GPU do you need for Granite Speech 5.0 2b?

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 Q6_K (1.5 GB file, about 2.7 GB in use).

Which Granite Speech 5.0 2b quant should you choose?

Q4_K_M is the usual starting point for Granite Speech 5.0 2b: it balances file size and quality well. Here it is a 1.1 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

Architecturegranite
Parameters1.84B
Layers40
Trained context16,384 tokens
KV cache (fp16)80 KB per token

Source

Quantized bymradermacher
FamilyGranite
Licenseapache-2.0
Downloads (HF)1,529
Last updated2026-10-22

Frequently asked questions about Granite Speech 5.0 2b

How much VRAM does Granite Speech 5.0 2b need?

About 2.3 GB at Q4_K_M with an 8K context window. That is the 1.1 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 5.0 2b on an 8 GB GPU?

Yes, with Q6_K: the 1.5 GB file needs about 2.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Granite Speech 5.0 2b GGUF?

It depends on the quant: file is 0.0 GB, IQ1_S is 0.5 GB, IQ1_M is 0.6 GB, IQ2_XXS is 0.6 GB, IQ2_XS is 0.6 GB, IQ2_S is 0.7 GB and 19 more.

What context length does Granite Speech 5.0 2b support?

The GGUF header lists a trained context length of 16,384 tokens (16K). The KV cache grows with the context you use: about 0.7 GB at 8K and 1.3 GB at 16K.

Where can I download Granite Speech 5.0 2b GGUF?

The files are on Hugging Face in the mradermacher/granite-speech-5.0-2b-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 Granite Speech 5.0 2b 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 Granite Speech 5.0 2B on 8 GB VRAM?

Yes, the Q4_0 quant requires about 2.3 GB memory at 8 k context, which fits in 8 GB VRAM.

Does this model support Japanese?

Yes, it supports Japanese for ASR and AST, as listed in its capabilities.

What license applies to this model?

The model is released under the Apache‑2.0 license.

Other GGUFs of granite-speech-5.0-2b

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Granite models

All Granite →

Other tiny models

All tiny models →