NVIDIA NemotronLabs VoiceChat 11B needs about 6.1 GB of memory at Q4_0 (a 5.0 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 6 quants, from 0.3 GB (Q4_0) to 22.2 GB (F16).
NVIDIA NemotronLabs VoiceChat 11B – 11B full‑duplex voice model
NVIDIA NemotronLabs VoiceChat 11B is an 11B end‑to‑end real‑time speech full‑duplex model. It performs streaming speech understanding, speech generation, and tool calling in one unified architecture. The model is available in GGUF format and runs with llama.cpp.
Good at
- Real‑time full‑duplex voice interaction
- Tool calling with natural conversation flow
- Unified speech understanding and generation
Limits
- No vision support
- No license details provided
- Requires specialized llama‑voicechat.cpp fork
Best for
- Voice assistant prototypes
- Research on full‑duplex speech models
- Tool‑enabled voice agents
Who it’s for. Researchers, developers, and professionals in NLP and speech technology who need an open‑source model for automatic speech recognition, text‑to‑speech synthesis, and voice assistant development.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_0 | 0.3 GB | 0.9 GB | Fits | Get file → | |
| Q4_0 | 0.7 GB | 1.3 GB | Fits | Get file → | |
| Q4_0 | 5.0 GB | 6.1 GB | Fits | Get file → | |
| Q4_0 | 6.6 GB | 7.9 GB | Tight | Get file → | |
| Q8_0 | 12.1 GB | 14.0 GB | Too big | Get file → | |
| F16 | 22.2 GB | 25.4 GB | Too big | Get file → |
For 8 GB VRAM use the Q4_0 0.33 GB file (≈0.9 GB memory at 8 k context). For 16 GB VRAM use the Q4_0 0.72 GB file (≈1.3 GB memory). For 24 GB VRAM use the Q4_0 5.02 GB file (≈6.1 GB memory).
What GPU do you need for NVIDIA NemotronLabs VoiceChat 11B?
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_0 (0.7 GB file, about 1.3 GB in use).
- 6 GB VRAM: the best quant that fits is Q4_0 (0.7 GB file, about 1.3 GB in use).
- 8 GB VRAM: the best quant that fits is Q4_0 (6.6 GB file, about 7.9 GB in use).
- 12 GB VRAM: the best quant that fits is Q4_0 (6.6 GB file, about 7.9 GB in use).
- 16 GB VRAM: the best quant that fits is Q8_0 (12.1 GB file, about 14.0 GB in use).
- 24 GB VRAM: the best quant that fits is Q8_0 (12.1 GB file, about 14.0 GB in use).
- 32 GB VRAM: the best quant that fits is F16 (22.2 GB file, about 25.4 GB in use).
Which NVIDIA NemotronLabs VoiceChat 11B quant should you choose?
Q4_0 (5.0 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_0 at 0.3 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
Source
Frequently asked questions about NVIDIA NemotronLabs VoiceChat 11B
How much VRAM does NVIDIA NemotronLabs VoiceChat 11B need?
About 6.1 GB at Q4_0 with an 8K context window. That is the 5.0 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 NVIDIA NemotronLabs VoiceChat 11B on an 8 GB GPU?
Yes, with Q4_0: the 6.6 GB file needs about 7.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of NVIDIA NemotronLabs VoiceChat 11B GGUF?
It depends on the quant: Q4_0 is 0.3 GB, Q4_0 is 0.7 GB, Q4_0 is 5.0 GB, Q4_0 is 6.6 GB, Q8_0 is 12.1 GB, F16 is 22.2 GB.
Where can I download NVIDIA NemotronLabs VoiceChat 11B GGUF?
The files are on Hugging Face in the hoidhxd/NVIDIA-NemotronLabs-VoiceChat-11B-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
Can I run this model on 8 GB VRAM?
Yes, the Q4_0 0.33 GB quantized file uses about 0.9 GB memory at 8 k context, which fits in 8 GB VRAM.
Does the model support languages other than English?
The model answers in English only; no other languages are supported.
What software is required to run the GGUF files?
Use llama.cpp with the sansamour/llama-voicechat.cpp fork and keep the four GGUF files in one folder.