VanMach 7B needs about 5.7 GB of memory at Q4_K_M (a 4.8 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 12 quants, from 3.1 GB (Q2_K) to 15.4 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 1.9 GB.
VanMach 7B – 7.71B‑parameter multilingual model for Vietnamese Chữ Nôm, Chinese, and English
VanMach 7B is a 7.71B‑parameter large language model built on qwen2 architecture. It focuses on Vietnamese Chữ Nôm, modern Vietnamese, and historical Hán‑Nôm documents. The model supports Vietnamese, Chinese, and English.
Good at
- Processing Vietnamese Chữ Nôm
- Handling historical Hán‑Nôm texts
- Multilingual support for Vietnamese, Chinese, English
Limits
- No vision support
- Requires large VRAM for higher‑quality quants
- License type is other
Best for
- Academic research on Vietnamese linguistics
- Translating historical documents
- Developing Vietnamese NLP tools
Who it’s for. Researchers and developers working on Vietnamese language studies, especially those needing accurate Chữ Nôm representation. Also suitable for multilingual NLP projects involving Vietnamese, Chinese, and English.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 3.1 GB | 4.0 GB | Fits | Get file → | |
| Q3_K_S | 3.6 GB | 4.5 GB | Fits | Get file → | |
| Q3_K_M | 3.9 GB | 4.8 GB | Fits | Get file → | |
| Q3_K_L | 4.1 GB | 5.1 GB | Fits | Get file → | |
| IQ4_XS | 4.3 GB | 5.3 GB | Fits | Get file → | |
| Q4_K_S | 4.5 GB | 5.5 GB | Fits | Get file → | |
| Q4_K_M | 4.8 GB | 5.7 GB | Fits | Get file → | |
| Q5_K_S | 5.4 GB | 6.4 GB | Fits | Get file → | |
| Q5_K_M | 5.5 GB | 6.5 GB | Fits | Get file → | |
| Q6_K | 6.3 GB | 7.3 GB | Tight | Get file → | |
| Q8_0 | 8.2 GB | 9.2 GB | Too big | Get file → | |
| F16 | 15.4 GB | 16.4 GB | Too big | Get file → |
For 8 GB VRAM, use Q4_K_M (file size 4.75 GB, estimated memory 5.7 GB). If more VRAM is available, Q5_K_M (5.52 GB, 6.5 GB) offers better quality. For the lowest memory footprint, Q2_K (3.07 GB, 4 GB) is an option but with reduced precision.
What GPU do you need for VanMach 7B?
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 Q2_K (3.1 GB file, about 4.0 GB in use).
- 6 GB VRAM: the best quant that fits is Q4_K_M (4.8 GB file, about 5.7 GB in use).
- 8 GB VRAM: the best quant that fits is Q6_K (6.3 GB file, about 7.3 GB in use).
- 12 GB VRAM: the best quant that fits is Q8_0 (8.2 GB file, about 9.2 GB in use).
- 16 GB VRAM: the best quant that fits is Q8_0 (8.2 GB file, about 9.2 GB in use).
- 24 GB VRAM: the best quant that fits is F16 (15.4 GB file, about 16.4 GB in use).
Which VanMach 7B quant should you choose?
Q4_K_M is the usual starting point for VanMach 7B: it balances file size and quality well. Here it is a 4.8 GB file.
The Q8_0 file is 8.2 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.
If memory is tight, the smallest file is Q2_K at 3.1 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about VanMach 7B
How much VRAM does VanMach 7B need?
About 5.7 GB at Q4_K_M with an 8K context window. That is the 4.8 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 VanMach 7B on an 8 GB GPU?
Yes, with Q6_K: the 6.3 GB file needs about 7.3 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of VanMach 7B GGUF?
It depends on the quant: Q2_K is 3.1 GB, Q3_K_S is 3.6 GB, Q3_K_M is 3.9 GB, Q3_K_L is 4.1 GB, IQ4_XS is 4.3 GB, Q4_K_S is 4.5 GB and 6 more.
What context length does VanMach 7B support?
The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 0.5 GB at 8K and 1.9 GB at 32K.
Where can I download VanMach 7B GGUF?
The files are on Hugging Face in the mradermacher/VanMach-7B-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 VanMach 7B use?
Hugging Face lists the license as other. 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 VanMach 7B on 8 GB VRAM?
Yes, the Q4_K_M quant uses about 5.7 GB of VRAM at 8 k context, which fits within 8 GB. For lower VRAM, use Q2_K or Q3_K_S.
Does VanMach 7B support image inputs?
No, the model does not have vision capabilities.
What languages can VanMach 7B understand?
It supports Vietnamese (Chữ Quốc ngữ and Chữ Nôm), Chinese (Simplified and Traditional), and English.