GR

Granite Speech 5.0 2b

GraniteGGUF by ibm-graniteUpdated 2026-10-26
Download on Hugging Face
Parameters1.84B
Context16K
Layers40
Architecturegranite
Smallest quant0.8 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 15 quants, from 0.8 GB (Q2_K) to 3.7 GB (BF16).

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

Granite Speech 5.0 2B is a 1.84B parameter model designed for automatic speech recognition and bidirectional speech translation in English, French, German, Spanish, Portuguese and Japanese. It was trained on 390,000 hours of audio and supports keyword‑biased ASR up to 2000 keywords.

Good at

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

Limits

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

Best for

  • Transcribing short‑form English speech
  • Translating conversational speech
  • Keyword‑biased search in audio

Who it’s for. Developers building speech‑to‑text or speech‑to‑speech applications that need a lightweight model with multilingual support. The model is suitable for edge deployments where memory is limited.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K0.8 GB 1.9 GB
Fits Get file →
Q3_K_S0.9 GB 2.0 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 →
Q4_01.1 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_01.3 GB 2.5 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 →
Q5_11.4 GB 2.6 GB
Fits Get file →
Q6_K1.5 GB 2.7 GB
Fits Get file →
Q8_02.0 GB 3.1 GB
Fits Get file →
BF163.7 GB 4.8 GB
Fits Get file →

For 8 GB VRAM use Q4_K or Q4_K_M (est. 2.3 GB). For 12 GB VRAM use Q5_K_M or Q5_1 (est. 2.5–2.6 GB). For 16 GB VRAM use Q6_K or Q8_0 (est. 2.7–3.1 GB).

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 Q8_0 (2.0 GB file, about 3.1 GB in use).
  • 6 GB VRAM: the best quant that fits is BF16 (3.7 GB file, about 4.8 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.

The Q8_0 file is 2.0 GB, about 1.7 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.

If memory is tight, the smallest file is Q2_K at 0.8 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

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

Source

Quantized byibm-granite
FamilyGranite
Licenseapache-2.0
Downloads (HF)3,398
Last updated2026-10-26

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 BF16: the 3.7 GB file needs about 4.8 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: Q2_K is 0.8 GB, Q3_K_S is 0.9 GB, Q3_K_M is 0.9 GB, Q3_K_L is 1.0 GB, Q4_0 is 1.1 GB, Q4_K_S is 1.1 GB and 9 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 ibm-granite/granite-speech-5.0-2b-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 this model on 8 GB VRAM?

Yes, use Q4_K or Q4_K_M quantizations; they require about 2.3 GB of VRAM at 8k context.

Does the model support vision tasks?

No, the model only supports speech and text modalities.

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 ibm-granite

All by ibm-granite →

More Granite models

All Granite →

Other tiny models

All tiny models →