Plamo 2 1b needs about 2.4 GB of memory at Q4_K_M (a 0.8 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 10 quants, from 0.7 GB (Q3_K_M) to 1.4 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.
1B Plamo 2 model, English and Japanese, GGUF format
Plamo 2 1B is a 1.29B parameter causal decoder‑only model pre‑trained on 4T tokens in English and Japanese. It uses a hybrid Samba architecture combining Mamba2 and sliding window attention. The model is not instruction‑tuned for chat or downstream tasks.
Good at
- English text generation
- Japanese text generation
- Causal decoding
Limits
- Not instruction tuned for chat
- No vision support
- Large context requires high VRAM
Best for
- Research on hybrid Samba architecture
- Low‑resource inference with small quants
- Japanese language tasks
Who it’s for. Developers and researchers who need a lightweight bilingual model for experimentation or to study Samba‑based architectures.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q3_K_M | 0.7 GB | 2.3 GB | Fits | Get file → | |
| Q3_K_L | 0.7 GB | 2.3 GB | Fits | Get file → | |
| Q4_0 | 0.8 GB | 2.4 GB | Fits | Get file → | |
| Q4_K_S | 0.8 GB | 2.4 GB | Fits | Get file → | |
| Q4_K_M | 0.8 GB | 2.4 GB | Fits | Get file → | |
| Q5_0 | 0.9 GB | 2.5 GB | Fits | Get file → | |
| Q5_K_S | 0.9 GB | 2.5 GB | Fits | Get file → | |
| Q5_K_M | 0.9 GB | 2.5 GB | Fits | Get file → | |
| Q6_K | 1.1 GB | 2.6 GB | Fits | Get file → | |
| Q8_0 | 1.4 GB | 2.9 GB | Fits | Get file → |
For 4 GB VRAM, use Q3_K_M or Q3_K_L (file size 0.69 GB or 0.72 GB, memory 2.3 GB at 8 k context). For 8 GB VRAM, Q4_0, Q4_K_S, or Q4_K_M (file size 0.78–0.82 GB, memory 2.4 GB). For 12 GB VRAM, Q5_0, Q5_K_S, or Q5_K_M (file size 0.92–0.94 GB, memory 2.5 GB).
What GPU do you need for Plamo 2 1b?
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 Q8_0 (1.4 GB file, about 2.9 GB in use).
Which Plamo 2 1b quant should you choose?
Q4_K_M is the usual starting point for Plamo 2 1b: it balances file size and quality well. Here it is a 0.8 GB file.
The Q8_0 file is 1.4 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 Q3_K_M at 0.7 GB, with the quality trade-offs that come with fewer bits. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Plamo 2 1b
How much VRAM does Plamo 2 1b need?
About 2.4 GB at Q4_K_M with an 8K context window. That is the 0.8 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 Plamo 2 1b on an 8 GB GPU?
Yes, with Q8_0: the 1.4 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 Plamo 2 1b GGUF?
It depends on the quant: Q3_K_M is 0.7 GB, Q3_K_L is 0.7 GB, Q4_0 is 0.8 GB, Q4_K_S is 0.8 GB, Q4_K_M is 0.8 GB, Q5_0 is 0.9 GB and 4 more.
What context length does Plamo 2 1b 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 1.1 GB at 8K and 4.3 GB at 32K.
Where can I download Plamo 2 1b GGUF?
The files are on Hugging Face in the mmnga/plamo-2-1b-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 1b 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 Plamo 2 1B on 4 GB VRAM?
Yes, using Q3_K_M or Q3_K_L quantization will fit within 4 GB VRAM with an estimated 2.3 GB memory usage at 8 k context.
Does it support Japanese language?
Yes, the model was pre‑trained on English and Japanese datasets and supports both languages.
Is the model instruction tuned for chat?
No, the model has not been instruction tuned for chat or other downstream tasks.