MN GRAND Gutenberg Lyra4 Lyra 23B V2 needs about 17.0 GB of memory at Q4_K_M (a 13.8 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 11 quants, from 8.7 GB (Q2_K) to 24.3 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 10.6 GB.
23B parameter Llama model for long‑form writing and roleplay
MN GRAND Gutenberg Lyra4 Lyra 23B V2 is a 22.9B parameter Llama model with a 1,024,000 token context. It excels in storytelling, prose, and role‑play scenarios. The model is released under the apache‑2.0 license.
Good at
- Long‑form storytelling
- Rich prose generation
- Role‑play with tools
Limits
- Large context requires high VRAM
- No vision support
- License is apache‑2.0
Best for
- Creative fiction writing
- Interactive role‑play sessions
- Narrative generation for games
Who it’s for. Developers and writers who need a large, text‑centric model for detailed storytelling. The model is suitable for applications that can allocate sufficient VRAM and support a 1,024,000 token context.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 8.7 GB | 11.9 GB | Too big | Get file → | |
| Q3_K_S | 10.1 GB | 13.3 GB | Too big | Get file → | |
| Q3_K_M | 11.2 GB | 14.3 GB | Too big | Get file → | |
| Q3_K_L | 12.1 GB | 15.3 GB | Too big | Get file → | |
| IQ4_XS | 12.5 GB | 15.7 GB | Too big | Get file → | |
| Q4_K_S | 13.1 GB | 16.3 GB | Too big | Get file → | |
| Q4_K_M | 13.8 GB | 17.0 GB | Too big | Get file → | |
| Q5_K_S | 15.8 GB | 19.0 GB | Too big | Get file → | |
| Q5_K_M | 16.2 GB | 19.4 GB | Too big | Get file → | |
| Q6_K | 18.8 GB | 21.9 GB | Too big | Get file → | |
| Q8_0 | 24.3 GB | 27.5 GB | Too big | Get file → |
For 8 GB VRAM, use Q2_K (file size 8.7 GB, estimated 11.9 GB memory at 8 k context). For 12 GB VRAM, Q3_K_S (10.1 GB, 13.3 GB memory) is a good balance. If 16 GB VRAM is available, Q4_K_S (13.14 GB, 16.3 GB memory) offers higher quality with manageable memory usage. All estimates are approximate.
What GPU do you need for MN GRAND Gutenberg Lyra4 Lyra 23B V2?
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: the best quant that fits is Q2_K (8.7 GB file, about 11.9 GB in use).
- 16 GB VRAM: the best quant that fits is IQ4_XS (12.5 GB file, about 15.7 GB in use).
- 24 GB VRAM: the best quant that fits is Q6_K (18.8 GB file, about 21.9 GB in use).
- 32 GB VRAM: the best quant that fits is Q8_0 (24.3 GB file, about 27.5 GB in use).
Which MN GRAND Gutenberg Lyra4 Lyra 23B V2 quant should you choose?
Q4_K_M is the usual starting point for MN GRAND Gutenberg Lyra4 Lyra 23B V2: it balances file size and quality well. Here it is a 13.8 GB file.
The Q8_0 file is 24.3 GB, about 1.8 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 8.7 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
Frequently asked questions about MN GRAND Gutenberg Lyra4 Lyra 23B V2
How much VRAM does MN GRAND Gutenberg Lyra4 Lyra 23B V2 need?
About 17.0 GB at Q4_K_M with an 8K context window. That is the 13.8 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 MN GRAND Gutenberg Lyra4 Lyra 23B V2 on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 11.9 GB, so you would need a larger GPU or CPU offloading.
What is the file size of MN GRAND Gutenberg Lyra4 Lyra 23B V2 GGUF?
It depends on the quant: Q2_K is 8.7 GB, Q3_K_S is 10.1 GB, Q3_K_M is 11.2 GB, Q3_K_L is 12.1 GB, IQ4_XS is 12.5 GB, Q4_K_S is 13.1 GB and 5 more.
What context length does MN GRAND Gutenberg Lyra4 Lyra 23B V2 support?
The GGUF header lists a trained context length of 1,024,000 tokens (1000K). The KV cache grows with the context you use: about 2.7 GB at 8K and 10.6 GB at 32K.
Where can I download MN GRAND Gutenberg Lyra4 Lyra 23B V2 GGUF?
The files are on Hugging Face in the DavidAU/MN-GRAND-Gutenberg-Lyra4-Lyra-23B-V2-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 MN GRAND Gutenberg Lyra4 Lyra 23B V2 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 this model on 8 GB VRAM?
Yes, the Q2_K quantized file is 8.7 GB and requires about 11.9 GB memory at 8 k context, which fits within 8 GB VRAM with efficient batching.
Does this model support vision?
No, the model does not have vision capabilities.
What license applies to this model?
The model is released under the apache‑2.0 license.