Lightning Herald 30B A3B needs about 33.0 GB of memory at Q4_K_M (a 25.4 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 5 quants, from 19.0 GB (IQ4_XS) to 35.0 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 28.5 GB.
Lightning Herald 30B A3B is a 32.9B-parameter Lightning model in GGUF format, quantized by EryriLabs. Its trained context length is 1024K tokens. The repository has 5 quant files, from 19.0 GB (IQ4_XS) to 35.0 GB (Q8_0).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ4_XS | 19.0 GB | 26.6 GB | Too big | Get file → | |
| Q4_K_M | 25.4 GB | 33.0 GB | Too big | Get file → | |
| Q5_K_M | 27.0 GB | 34.7 GB | Too big | Get file → | |
| Q6_K | 34.9 GB | 42.5 GB | Too big | Get file → | |
| Q8_0 | 35.0 GB | 42.6 GB | Too big | Get file → |
What GPU do you need for Lightning Herald 30B A3B?
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: no quant fits at an 8K context.
- 24 GB VRAM: no quant fits at an 8K context.
- 32 GB VRAM: the best quant that fits is IQ4_XS (19.0 GB file, about 26.6 GB in use).
- 48 GB VRAM: the best quant that fits is Q8_0 (35.0 GB file, about 42.6 GB in use).
Which Lightning Herald 30B A3B quant should you choose?
Q4_K_M is the usual starting point for Lightning Herald 30B A3B: it balances file size and quality well. Here it is a 25.4 GB file.
The Q8_0 file is 35.0 GB, about 1.4 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 IQ4_XS at 19.0 GB, with the quality trade-offs that come with fewer bits. The usual sweet spot between file size and quality, and the quant most people start with.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Lightning Herald 30B A3B
How much VRAM does Lightning Herald 30B A3B need?
About 33.0 GB at Q4_K_M with an 8K context window. That is the 25.4 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 Lightning Herald 30B A3B on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 26.6 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Lightning Herald 30B A3B GGUF?
It depends on the quant: IQ4_XS is 19.0 GB, Q4_K_M is 25.4 GB, Q5_K_M is 27.0 GB, Q6_K is 34.9 GB, Q8_0 is 35.0 GB.
What context length does Lightning Herald 30B A3B support?
The GGUF header lists a trained context length of 1,048,576 tokens (1024K). The KV cache grows with the context you use: about 7.1 GB at 8K and 28.5 GB at 32K.
Where can I download Lightning Herald 30B A3B GGUF?
The files are on Hugging Face in the EryriLabs/Lightning-Herald-30B-A3B-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 Lightning Herald 30B A3B 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.