Plamo 2 Translate needs about 7.5 GB of memory at Q4_K_M (a 6.3 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 37 quants, from 2.7 GB (IQ1_S) to 37.3 GB (F32).
PLaMo 2 Translate – a 9.53B parameter translation‑focused GGUF model
PLaMo 2 Translate is a 9.53B parameter model specialized for translation tasks. It is based on the plamo2 architecture and trained with a context length of 10485760 tokens. The model is available in multiple GGUF quantizations.
Good at
- High‑quality English‑Japanese translation
- Large context handling
- Low‑latency inference on GPU
Limits
- Not instruction‑tuned for chat
- No vision support
- License requires agreement for commercial use
Best for
- Batch translation pipelines
- Embedded translation in edge devices
- Research on multilingual translation
Who it’s for. Developers building translation services or research projects that need a dedicated translation model. The model is suitable for users who can comply with the PLaMo community license and have access to GPU resources for inference.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ1_S | 2.7 GB | 3.5 GB | Fits | Get file → | |
| TQ1_0 | 2.9 GB | 3.7 GB | Fits | Get file → | |
| IQ1_M | 2.9 GB | 3.8 GB | Fits | Get file → | |
| IQ2_XXS | 3.2 GB | 4.1 GB | Fits | Get file → | |
| TQ2_0 | 3.3 GB | 4.2 GB | Fits | Get file → | |
| IQ2_XS | 3.5 GB | 4.4 GB | Fits | Get file → | |
| IQ2_S | 3.6 GB | 4.5 GB | Fits | Get file → | |
| IQ2_M | 3.9 GB | 4.8 GB | Fits | Get file → | |
| Q2_K_S | 3.9 GB | 4.8 GB | Fits | Get file → | |
| Q2_K | 4.1 GB | 5.1 GB | Fits | Get file → | |
| IQ3_XXS | 4.3 GB | 5.4 GB | Fits | Get file → | |
| IQ3_XS | 4.6 GB | 5.6 GB | Fits | Get file → | |
| IQ3_S | 4.7 GB | 5.8 GB | Fits | Get file → | |
| Q3_K_S | 4.7 GB | 5.8 GB | Fits | Get file → | |
| IQ3_M | 4.9 GB | 5.9 GB | Fits | Get file → | |
| Q3_K | 5.1 GB | 6.2 GB | Fits | Get file → | |
| Q3_K_M | 5.1 GB | 6.2 GB | Fits | Get file → | |
| Q3_K_L | 5.4 GB | 6.6 GB | Fits | Get file → | |
| IQ4_XS | 5.7 GB | 6.9 GB | Fits | Get file → | |
| IQ4_XS | 5.7 GB | 6.9 GB | Fits | Get file → | |
| IQ4_NL | 6.0 GB | 7.2 GB | Fits | Get file → | |
| Q4_0 | 6.0 GB | 7.2 GB | Fits | Get file → | |
| Q4_K_S | 6.0 GB | 7.2 GB | Tight | Get file → | |
| Q4_K | 6.3 GB | 7.5 GB | Tight | Get file → | |
| Q4_K_M | 6.3 GB | 7.5 GB | Tight | Get file → | |
| Q4_1 | 6.5 GB | 7.8 GB | Tight | Get file → | |
| Q5_K_S | 7.1 GB | 8.4 GB | Too big | Get file → | |
| Q5_0 | 7.1 GB | 8.5 GB | Too big | Get file → | |
| Q5_K_M | 7.3 GB | 8.7 GB | Too big | Get file → | |
| Q5_K | 7.3 GB | 8.7 GB | Too big | Get file → | |
| Q5_K_M | 7.3 GB | 8.7 GB | Too big | Get file → | |
| Q5_1 | 7.7 GB | 9.1 GB | Too big | Get file → | |
| Q6_K | 8.3 GB | 9.8 GB | Too big | Get file → | |
| Q8_0 | 10.5 GB | 12.3 GB | Too big | Get file → | |
| BF16 | 19.1 GB | 21.8 GB | Too big | Get file → | |
| F16 | 19.1 GB | 21.8 GB | Too big | Get file → | |
| F32 | 37.3 GB | 42.3 GB | Too big | Get file → |
For 8 GB VRAM, use IQ1_S (file size 2.71 GB, memory 3.5 GB) or TQ1_0 (2.89 GB, 3.7 GB). For 12 GB VRAM, IQ4_XS (5.67 GB, 6.9 GB) or Q4_K (6.27 GB, 7.5 GB) are suitable. Higher precision quants like Q5_K_M (7.28 GB, 8.7 GB) require 16 GB or more.
What GPU do you need for Plamo 2 Translate?
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: the best quant that fits is IQ1_M (2.9 GB file, about 3.8 GB in use).
- 6 GB VRAM: the best quant that fits is IQ3_M (4.9 GB file, about 5.9 GB in use).
- 8 GB VRAM: the best quant that fits is Q4_1 (6.5 GB file, about 7.8 GB in use).
- 12 GB VRAM: the best quant that fits is Q6_K (8.3 GB file, about 9.8 GB in use).
- 16 GB VRAM: the best quant that fits is Q8_0 (10.5 GB file, about 12.3 GB in use).
- 24 GB VRAM: the best quant that fits is BF16 (19.1 GB file, about 21.8 GB in use).
- 32 GB VRAM: the best quant that fits is BF16 (19.1 GB file, about 21.8 GB in use).
- 48 GB VRAM: the best quant that fits is F32 (37.3 GB file, about 42.3 GB in use).
Which Plamo 2 Translate quant should you choose?
Q4_K_M is the usual starting point for Plamo 2 Translate: it balances file size and quality well. Here it is a 6.3 GB file.
The Q8_0 file is 10.5 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 IQ1_S at 2.7 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 Plamo 2 Translate
How much VRAM does Plamo 2 Translate need?
About 7.5 GB at Q4_K_M with an 8K context window. That is the 6.3 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 Plamo 2 Translate on an 8 GB GPU?
Yes, with Q4_1: the 6.5 GB file needs about 7.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Plamo 2 Translate GGUF?
It depends on the quant: IQ1_S is 2.7 GB, TQ1_0 is 2.9 GB, IQ1_M is 2.9 GB, IQ2_XXS is 3.2 GB, TQ2_0 is 3.3 GB, IQ2_XS is 3.5 GB and 31 more.
What context length does Plamo 2 Translate support?
The GGUF header lists a trained context length of 10,485,760 tokens (10240K).
Where can I download Plamo 2 Translate GGUF?
The files are on Hugging Face in the mitmul/plamo-2-translate-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 Plamo 2 Translate 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 PLaMo 2 Translate on 8 GB VRAM?
Yes, use IQ1_S or TQ1_0 quantizations, which require approximately 3.5–3.7 GB of VRAM at 8 k context.
Does the model support other languages besides English and Japanese?
The model was tested only in English and Japanese; other languages are not guaranteed to perform well.
Is the model suitable for chat applications?
No, the model is not instruction‑tuned for chat and is intended solely for translation tasks.