Gravity 30BA5B RL needs about 21.0 GB of memory at Q4_K_M (a 19.6 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 4 quants, from 13.1 GB (IQ3_XXS) to 26.6 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 3.7 GB.
Gravity 30BA5B RL is a 29.6B-parameter Gravity model in GGUF format, quantized by batiai. Its trained context length is 128K tokens. The repository has 4 quant files, from 13.1 GB (IQ3_XXS) to 26.6 GB (Q6_K).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ3_XXS | 13.1 GB | 14.6 GB | Too big | Get file → | |
| IQ4_XS | 16.1 GB | 17.5 GB | Too big | Get file → | |
| Q4_K_M | 19.6 GB | 21.0 GB | Too big | Get file → | |
| Q6_K | 26.6 GB | 28.0 GB | Too big | Get file → |
What GPU do you need for Gravity 30BA5B RL?
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: no quant fits at an 8K context.
- 16 GB VRAM: the best quant that fits is IQ3_XXS (13.1 GB file, about 14.6 GB in use).
- 24 GB VRAM: the best quant that fits is Q4_K_M (19.6 GB file, about 21.0 GB in use).
- 32 GB VRAM: the best quant that fits is Q6_K (26.6 GB file, about 28.0 GB in use).
Which Gravity 30BA5B RL quant should you choose?
Q4_K_M is the usual starting point for Gravity 30BA5B RL: it balances file size and quality well. Here it is a 19.6 GB file.
If memory is tight, the smallest file is IQ3_XXS at 13.1 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 Gravity 30BA5B RL
How much VRAM does Gravity 30BA5B RL need?
About 21.0 GB at Q4_K_M with an 8K context window. That is the 19.6 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 Gravity 30BA5B RL on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 14.6 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Gravity 30BA5B RL GGUF?
It depends on the quant: IQ3_XXS is 13.1 GB, IQ4_XS is 16.1 GB, Q4_K_M is 19.6 GB, Q6_K is 26.6 GB.
What context length does Gravity 30BA5B RL support?
The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 0.9 GB at 8K and 3.7 GB at 32K.
Where can I download Gravity 30BA5B RL GGUF?
The files are on Hugging Face in the batiai/Gravity-30BA5B-RL-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 Gravity 30BA5B RL 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.