GodziLLa 30B needs about 33.5 GB of memory at Q4_K_M (a 19.9 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 15 quants, from 12.3 GB (Q2_K) to 34.8 GB (Q8_0).
32.5B parameter LLaMA-based model for research and stress testing
GodziLLa-30B is an experimental combination of proprietary Maya LoRAs with CalderaAI's Lazarus-30B. It is 32.5B parameters, 2048 context tokens, and licensed under CC BY-NC 4.0 for non‑commercial use.
Good at
- Stress testing composite LLMs
- Benchmarking against open‑source LLMs
- Research on LoRA adapter behavior
Limits
- Commercial use prohibited
- No vision support
- Requires attribution under CC BY‑NC 4.0
Best for
- LLM research
- Benchmarking experiments
- Non‑commercial educational projects
Who it’s for. Researchers and developers exploring LoRA combinations and model limits. Suitable for non‑commercial academic work.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 12.3 GB | 16.1 GB | Too big | Get file → | |
| IQ3_XS | 13.6 GB | 17.3 GB | Too big | Get file → | |
| IQ3_S | 14.3 GB | 18.1 GB | Too big | Get file → | |
| Q3_K_S | 14.3 GB | 18.1 GB | Too big | Get file → | |
| IQ3_M | 15.1 GB | 18.9 GB | Too big | Get file → | |
| Q3_K_M | 16.0 GB | 19.8 GB | Too big | Get file → | |
| Q3_K_L | 17.5 GB | 21.3 GB | Too big | Get file → | |
| IQ4_XS | 17.7 GB | 21.5 GB | Too big | Get file → | |
| Q4_0 | 18.6 GB | 22.4 GB | Too big | Get file → | |
| Q4_K_S | 18.7 GB | 22.5 GB | Too big | Get file → | |
| Q4_K_M | 19.9 GB | 23.6 GB | Too big | Get file → | |
| Q5_K_S | 22.6 GB | 26.4 GB | Too big | Get file → | |
| Q5_K_M | 23.3 GB | 27.1 GB | Too big | Get file → | |
| Q6_K | 26.9 GB | 30.7 GB | Too big | Get file → | |
| Q8_0 | 34.8 GB | 38.5 GB | Too big | Get file → |
For 40 GB VRAM, Q6_K (26.94 GB) needs 40.5 GB memory, which is close to the limit. For 48 GB VRAM, Q8_0 (34.76 GB) needs 48.4 GB memory, suitable for full‑size runs. Smaller quants such as Q2_K (12.3 GB) still require 25.9 GB memory at 8k context, so they are not suitable for 8 GB VRAM. Memory estimates are approximate.
What GPU do you need for GodziLLa 30B?
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 (17.7 GB file, about 31.3 GB in use).
- 48 GB VRAM: the best quant that fits is Q6_K (26.9 GB file, about 40.5 GB in use).
Which GodziLLa 30B quant should you choose?
Q4_K_M is the usual starting point for GodziLLa 30B: it balances file size and quality well. Here it is a 19.9 GB file.
The Q8_0 file is 34.8 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 12.3 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 GodziLLa 30B
How much VRAM does GodziLLa 30B need?
About 33.5 GB at Q4_K_M with an 8K context window. That is the 19.9 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 GodziLLa 30B on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 25.9 GB, so you would need a larger GPU or CPU offloading.
What is the file size of GodziLLa 30B GGUF?
It depends on the quant: Q2_K is 12.3 GB, IQ3_XS is 13.6 GB, IQ3_S is 14.3 GB, Q3_K_S is 14.3 GB, IQ3_M is 15.1 GB, Q3_K_M is 16.0 GB and 9 more.
What context length does GodziLLa 30B support?
The GGUF header lists a trained context length of 2,048 tokens (2K). The KV cache grows with the context you use: about 13.1 GB at 8K and 3.3 GB at 2K.
Where can I download GodziLLa 30B GGUF?
The files are on Hugging Face in the mradermacher/GodziLLa-30B-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 GodziLLa 30B use?
Hugging Face lists the license as cc-by-nc-4.0. 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 GodziLLa-30B on 8 GB VRAM?
No, the smallest quant requires 25.9 GB memory at 8k context.
Is commercial use allowed?
No, CC BY‑NC 4.0 prohibits commercial use.
Do I need to provide attribution?
Yes, include attribution notice per license.