Plamo 2 Translate Eval needs about 10.4 GB of memory at Q4_K_M (a 5.6 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 12 quants, from 3.4 GB (Q2_K) to 18.2 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 17.2 GB.
Plamo 2 Translate Eval – 9.12B parameter translation evaluation model
Plamo 2 Translate Eval is a 9.12B parameter model specialized for translation evaluation. It is not instruction‑tuned for chat or other downstream tasks. The model is available in multiple GGUF quantizations.
Good at
- Translation evaluation
- Pair‑wise comparison
- English‑Japanese translation tasks
Limits
- No chat instruction tuning
- No vision support
- License requires agreement
Best for
- Evaluating translation quality
- Benchmarking translation systems
- Research on translation models
Who it’s for. Developers and researchers who need a dedicated translation evaluation model. The model is suitable for academic or commercial use under the PLaMo community license.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 3.4 GB | 8.2 GB | Too big | Get file → | |
| Q3_K_S | 4.1 GB | 8.9 GB | Too big | Get file → | |
| Q3_K_M | 4.5 GB | 9.3 GB | Too big | Get file → | |
| Q3_K_L | 4.8 GB | 9.5 GB | Too big | Get file → | |
| IQ4_XS | 5.0 GB | 9.8 GB | Too big | Get file → | |
| Q4_K_S | 5.3 GB | 10.1 GB | Too big | Get file → | |
| Q4_K_M | 5.6 GB | 10.4 GB | Too big | Get file → | |
| Q5_K_S | 6.3 GB | 11.1 GB | Too big | Get file → | |
| Q5_K_M | 6.5 GB | 11.3 GB | Too big | Get file → | |
| Q6_K | 7.5 GB | 12.3 GB | Too big | Get file → | |
| Q8_0 | 9.7 GB | 14.5 GB | Too big | Get file → | |
| F16 | 18.2 GB | 23.0 GB | Too big | Get file → |
For 8 GB VRAM, use Q2_K (3.45 GB, 8.2 GB memory) or Q3_K_S (4.08 GB, 8.9 GB memory). For 12 GB VRAM, Q4_K_M (5.56 GB, 10.4 GB memory) or Q5_K_S (6.33 GB, 11.1 GB memory) are suitable. Larger VRAM allows Q6_K or Q8_0 for higher quality.
What GPU do you need for Plamo 2 Translate Eval?
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: the best quant that fits is Q5_K_M (6.5 GB file, about 11.3 GB in use).
- 16 GB VRAM: the best quant that fits is Q8_0 (9.7 GB file, about 14.5 GB in use).
- 24 GB VRAM: the best quant that fits is F16 (18.2 GB file, about 23.0 GB in use).
Which Plamo 2 Translate Eval quant should you choose?
Q4_K_M is the usual starting point for Plamo 2 Translate Eval: it balances file size and quality well. Here it is a 5.6 GB file.
The Q8_0 file is 9.7 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 3.4 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 Eval
How much VRAM does Plamo 2 Translate Eval need?
About 10.4 GB at Q4_K_M with an 8K context window. That is the 5.6 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 Plamo 2 Translate Eval on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 8.2 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Plamo 2 Translate Eval GGUF?
It depends on the quant: Q2_K is 3.4 GB, Q3_K_S is 4.1 GB, Q3_K_M is 4.5 GB, Q3_K_L is 4.8 GB, IQ4_XS is 5.0 GB, Q4_K_S is 5.3 GB and 6 more.
What context length does Plamo 2 Translate Eval support?
The GGUF header lists a trained context length of 10,485,760 tokens (10240K). The KV cache grows with the context you use: about 4.3 GB at 8K and 17.2 GB at 32K.
Where can I download Plamo 2 Translate Eval GGUF?
The files are on Hugging Face in the mradermacher/plamo-2-translate-eval-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 Eval 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 Eval on 8 GB VRAM?
Yes, the Q2_K quantization is 3.45 GB and requires about 8.2 GB memory at 8k context.
Does this model support chat?
No, it has not been instruction‑tuned for chat or other downstream tasks.
What license does it use?
It is released under the PLaMo community license; users must agree before downloading.