Hebrew-GPT2-345M-Stage needs about 2.1 GB of memory at F16 (a 0.8 GB file) with an 8K context window, so it fits on a 4 GB GPU.
Hebrew-GPT2-345M-Stage: 0.406B parameter GPT‑2 model for Hebrew text generation
Hebrew-GPT2-345M-Stage is a 0.406B parameter GPT‑2 model trained on Hebrew text from "Bama Hadasha". It is available in GGUF format and supports 1024 token context. The model is released under the MIT license.
Good at
- Hebrew text generation
- Lightweight GPT‑2 architecture
- Fine‑tuned on niche Hebrew corpus
Limits
- No vision support
- Limited to 1024 token context
- Requires 8.1GB VRAM for F16 quant
Best for
- Generating short Hebrew passages
- Fine‑tuning on Hebrew datasets
- Testing Hebrew language models
Who it’s for. Developers and researchers needing a small Hebrew language model for experimentation or lightweight deployment. The model is suitable for educational projects and prototype applications.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| F16 | 0.8 GB | 1.4 GB | Fits | Get file → |
The only available quant is F16 with a file size of 0.82GB. It requires approximately 2.1GB of VRAM at 8k context. This is suitable for systems with at least 8GB VRAM. No other quantizations are provided.
What GPU do you need for Hebrew-GPT2-345M-Stage?
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 F16 (0.8 GB file, about 2.1 GB in use).
Which Hebrew-GPT2-345M-Stage quant should you choose?
F16 (0.8 GB) is the middle option in this repository. The unquantized model. It gives original quality and needs the most memory, so it is mainly for conversion or reference.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Hebrew-GPT2-345M-Stage
How much VRAM does Hebrew-GPT2-345M-Stage need?
About 2.1 GB at F16 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 Hebrew-GPT2-345M-Stage on an 8 GB GPU?
Yes, with F16: the 0.8 GB file needs about 2.1 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Hebrew-GPT2-345M-Stage GGUF?
It depends on the quant: F16 is 0.8 GB.
What context length does Hebrew-GPT2-345M-Stage support?
The GGUF header lists a trained context length of 1,024 tokens (1K). The KV cache grows with the context you use: about 0.8 GB at 8K and 0.1 GB at 1K.
Where can I download Hebrew-GPT2-345M-Stage GGUF?
The files are on Hugging Face in the Norod78/Hebrew-GPT2-345M-Stage repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does Hebrew-GPT2-345M-Stage use?
Hugging Face lists the license as mit. 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 Hebrew-GPT2-345M-Stage on 8 GB VRAM?
Yes, the F16 quant uses about 2.1GB VRAM at 8k context, leaving ample memory for other processes.
What license does this model use?
The model is released under the MIT license.
What is the maximum context length?
The model supports a maximum context length of 1024 tokens.