Lumosia v2 MoE 4x10.7 needs about 23.9 GB of memory at Q4_K_M (a 21.8 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 5 quants, from 17.3 GB (Q3_K_M) to 38.4 GB (Q8_0).
Lumosia v2 MoE 4x10.7 is a 36.1B-parameter Lumosia model in GGUF format, quantized by nold. Its trained context length is 4K tokens. The repository has 5 quant files, from 17.3 GB (Q3_K_M) to 38.4 GB (Q8_0).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q3_K_M | 17.3 GB | 18.6 GB | Too big | Get file → | |
| Q4_K_M | 21.8 GB | 23.1 GB | Too big | Get file → | |
| Q5_K_M | 25.6 GB | 26.9 GB | Too big | Get file → | |
| Q6_K | 29.6 GB | 30.9 GB | Too big | Get file → | |
| Q8_0 | 38.4 GB | 39.7 GB | Too big | Get file → |
What GPU do you need for Lumosia v2 MoE 4x10.7?
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: the best quant that fits is Q4_K_M (21.8 GB file, about 23.9 GB in use).
- 32 GB VRAM: the best quant that fits is Q6_K (29.6 GB file, about 31.7 GB in use).
- 48 GB VRAM: the best quant that fits is Q8_0 (38.4 GB file, about 40.5 GB in use).
Which Lumosia v2 MoE 4x10.7 quant should you choose?
Q4_K_M is the usual starting point for Lumosia v2 MoE 4x10.7: it balances file size and quality well. Here it is a 21.8 GB file.
The Q8_0 file is 38.4 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 Q3_K_M at 17.3 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 Lumosia v2 MoE 4x10.7
How much VRAM does Lumosia v2 MoE 4x10.7 need?
About 23.9 GB at Q4_K_M with an 8K context window. That is the 21.8 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 Lumosia v2 MoE 4x10.7 on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 19.4 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Lumosia v2 MoE 4x10.7 GGUF?
It depends on the quant: Q3_K_M is 17.3 GB, Q4_K_M is 21.8 GB, Q5_K_M is 25.6 GB, Q6_K is 29.6 GB, Q8_0 is 38.4 GB.
What context length does Lumosia v2 MoE 4x10.7 support?
The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 1.6 GB at 8K and 0.8 GB at 4K.
Where can I download Lumosia v2 MoE 4x10.7 GGUF?
The files are on Hugging Face in the nold/Lumosia-v2-MoE-4x10.7-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 Lumosia v2 MoE 4x10.7 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.