moshiko candle q8 needs about 9.6 GB of memory at its main file (a 8.2 GB file) with an 8K context window, so it fits on a 12 GB GPU.
Moshiko Candle Q8 – 7.69B speech‑text foundation model
Moshiko Candle Q8 is a 7.69 billion‑parameter speech‑text foundation model quantized to 8 bits. It generates speech tokens from a neural audio codec while predicting time‑aligned text tokens. The model supports real‑time full‑duplex dialogue with a theoretical latency of 160 ms.
Good at
- Real‑time spoken dialogue
- Speech‑to‑speech generation
- Time‑aligned text prediction
Limits
- No vision support
- Limited complex task handling
- Requires 9.6 GB VRAM at 8 k context
Best for
- Low‑latency voice assistants
- Speech‑to‑speech conversion
- Streaming speech recognition
Who it’s for. Developers building voice‑enabled conversational agents who need a lightweight, real‑time solution. The model is suitable for applications that prioritize low latency over advanced reasoning or tool use.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 8.2 GB | 9.6 GB | Too big | Get file → |
For 8 GB VRAM, use the Q8 quantized file (8.17 GB). The estimated VRAM usage is 9.6 GB at 8 k context, so the model will run close to the limit. If more VRAM is available, the same file can be used for higher context lengths.
What GPU do you need for moshiko candle q8?
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: no quant fits at an 8K context.
- 6 GB VRAM: no quant fits at an 8K context.
- 8 GB VRAM: no quant fits at an 8K context.
- 12 GB VRAM: the best quant that fits is the main file (8.2 GB file, about 9.6 GB in use).
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about moshiko candle q8
How much VRAM does moshiko candle q8 need?
About 9.6 GB at its main file with an 8K context window. That is the 8.2 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 moshiko candle q8 on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 9.6 GB, so you would need a larger GPU or CPU offloading.
What is the file size of moshiko candle q8 GGUF?
It depends on the quant: file is 8.2 GB.
Where can I download moshiko candle q8 GGUF?
The files are on Hugging Face in the kyutai/moshiko-candle-q8 repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does moshiko candle q8 use?
Hugging Face lists the license as cc-by-4.0. 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 Moshiko Candle Q8 on 8 GB VRAM?
The model requires 9.6 GB VRAM at 8 k context, so it will not fit on 8 GB VRAM without swapping or reducing context.
Does Moshiko Candle Q8 support vision?
No, the model is a speech‑text foundation model and does not include vision capabilities.