ChindaMT 2B needs about 2.5 GB of memory at Q4_K_M (a 1.6 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 25 quants, from 0.0 GB to 2.0 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 1.6 GB.
ChindaMT 2B – Thai‑English instruction‑following translation
ChindaMT 2B is a 2.39B‑parameter model fine‑tuned from Qwen3.5‑2B for Thai‑English machine translation. It follows user‑supplied rules such as terminology, register, length, and output format. The model is released under Apache‑2.0 and is available in multiple GGUF quantizations.
Good at
- Instruction‑following translation
- Rule‑based output formatting
- Bidirectional Thai‑English translation
Limits
- Requires 8‑k context for best performance
- No vision support
- Large memory for higher‑quality quants
Best for
- Developers building translation tools
- Researchers testing rule‑based MT
- Deployments needing lightweight Thai‑English models
Who it’s for. Engineers and researchers who need a Thai‑English translation model that can follow detailed instructions. The model is suitable for integration into chat or translation applications where rule compliance is important.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.0 GB | 0.9 GB | Fits | Get file → | |
| IQ1_S | 0.9 GB | 1.8 GB | Fits | Get file → | |
| IQ1_M | 0.9 GB | 1.8 GB | Fits | Get file → | |
| IQ2_XXS | 1.0 GB | 1.9 GB | Fits | Get file → | |
| IQ2_XS | 1.0 GB | 1.9 GB | Fits | Get file → | |
| IQ2_S | 1.1 GB | 2.0 GB | Fits | Get file → | |
| IQ2_M | 1.1 GB | 2.0 GB | Fits | Get file → | |
| Q2_K_S | 1.1 GB | 2.0 GB | Fits | Get file → | |
| Q2_K | 1.1 GB | 2.0 GB | Fits | Get file → | |
| IQ3_XXS | 1.1 GB | 2.0 GB | Fits | Get file → | |
| Q3_K_S | 1.2 GB | 2.1 GB | Fits | Get file → | |
| IQ3_XS | 1.2 GB | 2.1 GB | Fits | Get file → | |
| IQ3_S | 1.3 GB | 2.2 GB | Fits | Get file → | |
| IQ3_M | 1.3 GB | 2.2 GB | Fits | Get file → | |
| Q3_K_M | 1.3 GB | 2.2 GB | Fits | Get file → | |
| Q3_K_L | 1.4 GB | 2.3 GB | Fits | Get file → | |
| IQ4_XS | 1.5 GB | 2.4 GB | Fits | Get file → | |
| Q4_0 | 1.5 GB | 2.4 GB | Fits | Get file → | |
| Q4_K_S | 1.5 GB | 2.4 GB | Fits | Get file → | |
| IQ4_NL | 1.5 GB | 2.4 GB | Fits | Get file → | |
| Q4_K_M | 1.6 GB | 2.5 GB | Fits | Get file → | |
| Q4_1 | 1.6 GB | 2.5 GB | Fits | Get file → | |
| Q5_K_S | 1.7 GB | 2.6 GB | Fits | Get file → | |
| Q5_K_M | 1.8 GB | 2.7 GB | Fits | Get file → | |
| Q6_K | 2.0 GB | 2.9 GB | Fits | Get file → |
For 8‑GB VRAM, use Q4_0 (1.49 GB, ~2.4 GB memory) or Q4_K_S (1.5 GB, ~2.4 GB memory). For 12‑GB VRAM, Q5_K_S (1.72 GB, ~2.6 GB memory) or Q5_K_M (1.76 GB, ~2.7 GB memory) provide a good balance of size and quality. Higher‑quality quants such as Q6_K (1.97 GB, ~2.9 GB memory) require more memory but offer the best precision.
What GPU do you need for ChindaMT 2B?
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 Q6_K (2.0 GB file, about 2.9 GB in use).
Which ChindaMT 2B quant should you choose?
Q4_K_M is the usual starting point for ChindaMT 2B: it balances file size and quality well. Here it is a 1.6 GB file.
If memory is tight, the smallest file is the first one in the table at 0.0 GB, with the quality trade-offs that come with fewer bits.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about ChindaMT 2B
How much VRAM does ChindaMT 2B need?
About 2.5 GB at Q4_K_M with an 8K context window. That is the 1.6 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 ChindaMT 2B on an 8 GB GPU?
Yes, with Q6_K: the 2.0 GB file needs about 2.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of ChindaMT 2B GGUF?
It depends on the quant: file is 0.0 GB, IQ1_S is 0.9 GB, IQ1_M is 0.9 GB, IQ2_XXS is 1.0 GB, IQ2_XS is 1.0 GB, IQ2_S is 1.1 GB and 19 more.
What context length does ChindaMT 2B support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 0.4 GB at 8K and 1.6 GB at 32K.
Where can I download ChindaMT 2B GGUF?
The files are on Hugging Face in the mradermacher/ChindaMT-2B-i1-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 ChindaMT 2B 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 ChindaMT 2B on 8 GB VRAM?
Yes, with a Q4_0 or Q4_K_S quant, which are about 1.5 GB in size and use roughly 2.4 GB of VRAM at 8‑k context.
Does this model support vision tasks?
No, ChindaMT 2B is a text‑only model; no mmproj files are provided.
What license applies to this model?
The model is released under the Apache‑2.0 license, inherited from its base model.