moshika 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.
Moshika Candle Q8 – 7.69B speech‑text foundation model
Moshika Candle Q8 is a 7.69‑billion‑parameter speech‑text foundation model. It generates speech tokens from a neural audio codec and predicts time‑aligned text tokens. The model is quantized to 8‑bit precision and licensed under CC‑BY‑4.0.
Good at
- Real‑time full‑duplex spoken dialogue
- Low‑latency speech generation
- Streaming speech recognition
Limits
- No vision support
- Limited complex task handling
- Requires 8‑bit quantization only
Best for
- Casual conversational agents
- Speech‑to‑speech generation
- Low‑latency TTS
Who it’s for. Developers building real‑time spoken dialogue systems or low‑latency TTS solutions. The model is suitable for applications that need natural, low‑latency interactions without complex tool access.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 8.2 GB | 9.6 GB | Too big | Get file → |
The Q8 quantized file is 8.17 GB and requires approximately 9.6 GB of VRAM at 8 k context. For 8 GB VRAM, the model will not fit; a smaller quantization or a different model is needed.
What GPU do you need for moshika 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 moshika candle q8
How much VRAM does moshika 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 moshika 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 moshika candle q8 GGUF?
It depends on the quant: file is 8.2 GB.
Where can I download moshika candle q8 GGUF?
The files are on Hugging Face in the kyutai/moshika-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 moshika 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 Moshika Candle Q8 on 8 GB VRAM?
No. The 8.17 GB file needs about 9.6 GB VRAM at 8 k context, exceeding an 8 GB limit.
Does the model support vision tasks?
No. It is a speech‑text foundation model with no vision capabilities.