GR

Granite Speech 3.2 8b

GraniteGGUF by mradermacherUpdated 2026-10-21
Download on Hugging Face
Parameters8.17B
Context128K
Layers40
Architecturegranite
Smallest quant0.0 GB
Quick answer

Granite Speech 3.2 8b needs about 6.8 GB of memory at Q4_K_M (a 4.9 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 25 quants, from 0.0 GB to 6.7 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 5.4 GB.

Granite Speech 3.2 8b – compact speech‑to‑text and translation model

Granite Speech 3.2 8b is a 8.17 b parameter model designed for automatic speech recognition and speech translation. It uses a two‑pass design, requiring separate calls for transcription and language processing. The model supports English and major European languages, Japanese, and Mandarin.

Good at

  • English speech‑to‑text
  • Speech translation to major European languages
  • Two‑pass ASR and AST workflow

Limits

  • No vision support
  • Requires two separate calls
  • License is Apache‑2.0

Best for

  • Enterprise speech‑to‑text pipelines
  • Multilingual speech translation services
  • Audio transcription for content creation

Who it’s for. Developers building enterprise applications that process speech inputs. The model is suitable for English speech‑to‑text and translation from English to French, Spanish, Italian, German, Portuguese, Japanese, and Mandarin.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 1.9 GB
Fits Get file →
IQ1_S1.8 GB 3.7 GB
Fits Get file →
IQ1_M2.0 GB 3.8 GB
Fits Get file →
IQ2_XXS2.3 GB 4.1 GB
Fits Get file →
IQ2_XS2.5 GB 4.3 GB
Fits Get file →
IQ2_S2.6 GB 4.5 GB
Fits Get file →
IQ2_M2.8 GB 4.7 GB
Fits Get file →
Q2_K_S2.9 GB 4.7 GB
Fits Get file →
Q2_K3.1 GB 4.9 GB
Fits Get file →
IQ3_XXS3.2 GB 5.0 GB
Fits Get file →
IQ3_XS3.4 GB 5.3 GB
Fits Get file →
Q3_K_S3.6 GB 5.4 GB
Fits Get file →
IQ3_S3.6 GB 5.5 GB
Fits Get file →
IQ3_M3.7 GB 5.6 GB
Fits Get file →
Q3_K_M4.0 GB 5.8 GB
Fits Get file →
Q3_K_L4.3 GB 6.2 GB
Fits Get file →
IQ4_XS4.4 GB 6.3 GB
Fits Get file →
Q4_04.7 GB 6.5 GB
Fits Get file →
IQ4_NL4.7 GB 6.5 GB
Fits Get file →
Q4_K_S4.7 GB 6.5 GB
Fits Get file →
Q4_K_M4.9 GB 6.8 GB
Fits Get file →
Q4_15.1 GB 7.0 GB
Fits Get file →
Q5_K_S5.6 GB 7.5 GB
Tight Get file →
Q5_K_M5.8 GB 7.6 GB
Tight Get file →
Q6_K6.7 GB 8.5 GB
Too big Get file →

For 8 GB VRAM, use Q4_K_M (file size 4.94 GB, estimated 6.8 GB memory). For 12 GB VRAM, Q5_K_M (5.8 GB, 7.6 GB memory) or Q6_K (6.71 GB, 8.5 GB memory). For 4 GB VRAM, IQ1_S (1.84 GB, 3.7 GB memory) or IQ1_M (2 GB, 3.8 GB memory).

What GPU do you need for Granite Speech 3.2 8b?

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 IQ1_M (2.0 GB file, about 3.8 GB in use).
  • 6 GB VRAM: the best quant that fits is Q3_K_M (4.0 GB file, about 5.8 GB in use).
  • 8 GB VRAM: the best quant that fits is Q5_K_M (5.8 GB file, about 7.6 GB in use).
  • 12 GB VRAM: the best quant that fits is Q6_K (6.7 GB file, about 8.5 GB in use).

Which Granite Speech 3.2 8b quant should you choose?

Q4_K_M is the usual starting point for Granite Speech 3.2 8b: it balances file size and quality well. Here it is a 4.9 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
Parameters8.17B
Layers40
Trained context131,072 tokens
KV cache (fp16)160 KB per token

Source

Quantized bymradermacher
FamilyGranite
Licenseapache-2.0
Downloads (HF)1,414
Last updated2026-10-21

Frequently asked questions about Granite Speech 3.2 8b

How much VRAM does Granite Speech 3.2 8b need?

About 6.8 GB at Q4_K_M with an 8K context window. That is the 4.9 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 3.2 8b on an 8 GB GPU?

Yes, with Q5_K_M: the 5.8 GB file needs about 7.6 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Granite Speech 3.2 8b GGUF?

It depends on the quant: file is 0.0 GB, IQ1_S is 1.8 GB, IQ1_M is 2.0 GB, IQ2_XXS is 2.3 GB, IQ2_XS is 2.5 GB, IQ2_S is 2.6 GB and 19 more.

What context length does Granite Speech 3.2 8b support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 1.3 GB at 8K and 5.4 GB at 32K.

Where can I download Granite Speech 3.2 8b GGUF?

The files are on Hugging Face in the mradermacher/granite-speech-3.2-8b-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 3.2 8b 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 3.2 8b on 8 GB VRAM?

Yes, the Q4_K_M quant uses about 6.8 GB memory at 8k context, fitting within 8 GB VRAM.

Does this model support vision tasks?

No, it is a speech‑only model; no vision support is provided.

What license applies to this model?

The model is released under the Apache‑2.0 license.

Other GGUFs of granite-speech-3.2-8b

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Granite models

All Granite →

Other small models

All small models →