LL

ultravox v0 5 llama 3 2 1b

LlamaGGUF by ggml-orgUpdated 2025-05-25
Download on Hugging Face
Parameters1.24B
Context128K
Layers16
Architecturellama
Smallest quant0.8 GB
Quick answer

ultravox v0 5 llama 3 2 1b needs about 1.6 GB of memory at Q4_K_M (a 0.8 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 2 quants, from 0.8 GB (Q4_K_M) to 1.3 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 1.1 GB.

Ultravox v0.5: a multimodal Speech LLM based on Llama3.2-1B

Ultravox v0.5 is a multimodal model that accepts speech and text as input. It uses a Llama3.2-1B-Instruct backbone and a Whisper-large-v3-turbo encoder. The model generates text output from combined audio and text embeddings.

Good at

  • Speech-to-text conversion
  • Voice agent interactions
  • Speech translation

Limits

  • No vision support
  • Requires 8k context for memory estimates
  • MIT license only

Best for

  • Voice assistants
  • Speech analytics
  • Audio‑to‑text pipelines

Who it’s for. Developers building voice‑enabled applications that need text generation from spoken input. The model is suitable for research and prototyping of multimodal LLMs.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M0.8 GB 1.6 GB
Fits Get file →
Q8_01.3 GB 2.1 GB
Fits Get file →

For 8 GB VRAM, use Q4_K_M (0.81 GB, ~1.6 GB memory at 8k context). For 12 GB VRAM, Q8_0 (1.32 GB, ~2.1 GB memory at 8k context) provides higher precision.

What GPU do you need for ultravox v0 5 llama 3 2 1b?

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 (1.3 GB file, about 2.1 GB in use).

Which ultravox v0 5 llama 3 2 1b quant should you choose?

Q4_K_M is the usual starting point for ultravox v0 5 llama 3 2 1b: it balances file size and quality well. Here it is a 0.8 GB file.

The Q8_0 file is 1.3 GB, about 1.6 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.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters1.24B
Layers16
Trained context131,072 tokens
KV cache (fp16)32 KB per token

Source

Quantized byggml-org
FamilyLlama
Licensemit
Downloads (HF)7,399
Last updated2025-05-25

Frequently asked questions about ultravox v0 5 llama 3 2 1b

How much VRAM does ultravox v0 5 llama 3 2 1b need?

About 1.6 GB at Q4_K_M with an 8K context window. That is the 0.8 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 ultravox v0 5 llama 3 2 1b on an 8 GB GPU?

Yes, with Q8_0: the 1.3 GB file needs about 2.1 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of ultravox v0 5 llama 3 2 1b GGUF?

It depends on the quant: Q4_K_M is 0.8 GB, Q8_0 is 1.3 GB.

What context length does ultravox v0 5 llama 3 2 1b support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 0.3 GB at 8K and 1.1 GB at 32K.

Where can I download ultravox v0 5 llama 3 2 1b GGUF?

The files are on Hugging Face in the ggml-org/ultravox-v0_5-llama-3_2-1b-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 ultravox v0 5 llama 3 2 1b use?

Hugging Face lists the license as mit. 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 Ultravox on 8 GB VRAM?

Yes, the Q4_K_M quantized model is 0.81 GB and requires about 1.6 GB memory at 8k context, which fits within 8 GB VRAM.

Does Ultravox support image input?

No, Ultravox only supports speech and text input; it has no vision capability.

What license does Ultravox use?

Ultravox is released under the MIT license.

Similar models

Browse all →

More from ggml-org

All by ggml-org →

More Llama models

All Llama →

Other tiny models

All tiny models →