MN 12B Lyra v4 needs about 10.4 GB of memory at Q5_0 (a 8.5 GB file) with an 8K context window, so it fits on a 12 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 5.4 GB.
MN 12B Lyra v4 is a 12.2B-parameter Lyra model in GGUF format, quantized by EloyOn. Its trained context length is 1000K tokens. The repository has 1 quant file, from 8.5 GB (Q5_0) to 8.5 GB (Q5_0).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q5_0 | 8.5 GB | 10.4 GB | Too big | Get file → |
What GPU do you need for MN 12B Lyra v4?
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 Q5_0 (8.5 GB file, about 10.4 GB in use).
Which MN 12B Lyra v4 quant should you choose?
Q5_0 (8.5 GB) is the middle option in this repository. Closer to the original model than 4-bit, for a moderate increase in size. A good pick when you have memory to spare.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about MN 12B Lyra v4
How much VRAM does MN 12B Lyra v4 need?
About 10.4 GB at Q5_0 with an 8K context window. That is the 8.5 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 12B Lyra v4 on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 10.4 GB, so you would need a larger GPU or CPU offloading.
What is the file size of MN 12B Lyra v4 GGUF?
It depends on the quant: Q5_0 is 8.5 GB.
What context length does MN 12B Lyra v4 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 1.3 GB at 8K and 5.4 GB at 32K.
Where can I download MN 12B Lyra v4 GGUF?
The files are on Hugging Face in the EloyOn/MN-12B-Lyra-v4-Q5_0-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 12B Lyra v4 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.