mOrpheus_3B 1Base_early_preview v1 25000 needs about 3.5 GB of memory at Q4_K_M (a 2.1 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 11 quants, from 2.0 GB (Q4_0) to 6.6 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 3.8 GB.
mOrpheus_3B 1Base_early_preview v1 25000 is a 3.3B-parameter Morpheus model in GGUF format, quantized by joyoh. Its trained context length is 128K tokens. The repository has 11 quant files, from 2.0 GB (Q4_0) to 6.6 GB (F16).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_0 | 2.0 GB | 3.4 GB | Fits | Get file → | |
| Q4_K_S | 2.0 GB | 3.4 GB | Fits | Get file → | |
| Q4_K_M | 2.1 GB | 3.5 GB | Fits | Get file → | |
| Q4_1 | 2.2 GB | 3.6 GB | Fits | Get file → | |
| Q5_0 | 2.3 GB | 3.8 GB | Fits | Get file → | |
| Q5_K_S | 2.3 GB | 3.8 GB | Fits | Get file → | |
| Q5_K_M | 2.4 GB | 3.8 GB | Fits | Get file → | |
| Q5_1 | 2.5 GB | 4.0 GB | Fits | Get file → | |
| Q6_K | 2.7 GB | 4.2 GB | Fits | Get file → | |
| Q8_0 | 3.5 GB | 5.0 GB | Fits | Get file → | |
| F16 | 6.6 GB | 8.1 GB | Too big | Get file → |
What GPU do you need for mOrpheus_3B 1Base_early_preview v1 25000?
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: the best quant that fits is Q5_1 (2.5 GB file, about 4.0 GB in use).
- 6 GB VRAM: the best quant that fits is Q8_0 (3.5 GB file, about 5.0 GB in use).
- 8 GB VRAM: the best quant that fits is Q8_0 (3.5 GB file, about 5.0 GB in use).
- 12 GB VRAM: the best quant that fits is F16 (6.6 GB file, about 8.1 GB in use).
Which mOrpheus_3B 1Base_early_preview v1 25000 quant should you choose?
Q4_K_M is the usual starting point for mOrpheus_3B 1Base_early_preview v1 25000: it balances file size and quality well. Here it is a 2.1 GB file.
The Q8_0 file is 3.5 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 Q4_0 at 2.0 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
Frequently asked questions about mOrpheus_3B 1Base_early_preview v1 25000
How much VRAM does mOrpheus_3B 1Base_early_preview v1 25000 need?
About 3.5 GB at Q4_K_M with an 8K context window. That is the 2.1 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 mOrpheus_3B 1Base_early_preview v1 25000 on an 8 GB GPU?
Yes, with Q8_0: the 3.5 GB file needs about 5.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of mOrpheus_3B 1Base_early_preview v1 25000 GGUF?
It depends on the quant: Q4_0 is 2.0 GB, Q4_K_S is 2.0 GB, Q4_K_M is 2.1 GB, Q4_1 is 2.2 GB, Q5_0 is 2.3 GB, Q5_K_S is 2.3 GB and 5 more.
What context length does mOrpheus_3B 1Base_early_preview v1 25000 support?
The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 0.9 GB at 8K and 3.8 GB at 32K.
Where can I download mOrpheus_3B 1Base_early_preview v1 25000 GGUF?
The files are on Hugging Face in the joyoh/mOrpheus_3B-1Base_early_preview-v1-25000_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 mOrpheus_3B 1Base_early_preview v1 25000 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.