Hy-SimulMT-30B-A3B-Interleave needs about 21.1 GB of memory at Q4_K_M (a 19.7 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 2 quants, from 19.7 GB (Q4_K_M) to 33.3 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 3.2 GB.
Real‑time simultaneous Chinese‑English translation model
Hy‑SimulMT‑30B‑A3B‑Interleave is a 30.4B parameter model designed for real‑time simultaneous translation. It supports bidirectional speech‑to‑speech between Chinese and English and includes real‑time voice cloning. The model is trained on 262144 context tokens and licensed under Apache‑2.0.
Good at
- Real‑time simultaneous translation
- Speech‑to‑speech with voice cloning
- Reasoning and tool use
Limits
- No vision support
- Large VRAM requirement
- Mixture of experts active parameters 3B
Best for
- Live meetings and conferences
- Real‑time interviews
- Speech‑to‑speech translation apps
Who it’s for. Developers building real‑time translation services or applications that require low‑latency speech‑to‑speech between Chinese and English. The model is suitable for systems with sufficient GPU memory to load the 30.4B parameters.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 19.7 GB | 21.1 GB | Too big | Get file → | |
| Q8_0 | 33.3 GB | 34.6 GB | Too big | Get file → |
For 8‑GB VRAM use the Q4_K_M quantized file (19.75 GB, ~21.1 GB memory at 8k context). For larger memory budgets the Q8_0 file (33.31 GB, ~34.6 GB memory at 8k context) provides higher precision.
What GPU do you need for Hy-SimulMT-30B-A3B-Interleave?
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: 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: no quant fits at an 8K context.
- 16 GB VRAM: no quant fits at an 8K context.
- 24 GB VRAM: the best quant that fits is Q4_K_M (19.7 GB file, about 21.1 GB in use).
- 32 GB VRAM: the best quant that fits is Q4_K_M (19.7 GB file, about 21.1 GB in use).
- 48 GB VRAM: the best quant that fits is Q8_0 (33.3 GB file, about 34.6 GB in use).
Which Hy-SimulMT-30B-A3B-Interleave quant should you choose?
Q4_K_M is the usual starting point for Hy-SimulMT-30B-A3B-Interleave: it balances file size and quality well. Here it is a 19.7 GB file.
The Q8_0 file is 33.3 GB, about 1.7 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
Frequently asked questions about Hy-SimulMT-30B-A3B-Interleave
How much VRAM does Hy-SimulMT-30B-A3B-Interleave need?
About 21.1 GB at Q4_K_M with an 8K context window. That is the 19.7 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 Hy-SimulMT-30B-A3B-Interleave on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 21.1 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Hy-SimulMT-30B-A3B-Interleave GGUF?
It depends on the quant: Q4_K_M is 19.7 GB, Q8_0 is 33.3 GB.
What context length does Hy-SimulMT-30B-A3B-Interleave support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 0.8 GB at 8K and 3.2 GB at 32K.
Where can I download Hy-SimulMT-30B-A3B-Interleave GGUF?
The files are on Hugging Face in the tencent/Hy-SimulMT-30B-A3B-Interleave-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 Hy-SimulMT-30B-A3B-Interleave 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 this model on 8 GB VRAM?
The Q4_K_M quantized file requires about 21.1 GB of VRAM at 8k context, so 8 GB VRAM is insufficient.
What license does this model use?
The model is released under the Apache‑2.0 license.
Does the model support vision tasks?
No, the model does not support vision.