RainbowsEdge-v0.1-rc1-18B needs about 16.3 GB of memory at Q5_K_M (a 13.1 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 2 quants, from 13.1 GB (Q5_K_M) to 19.7 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 10.7 GB.
RainbowsEdge-v0.1-rc1-18B is a 18.5B-parameter Rainbowsedge model in GGUF format, quantized by invisietch. Its trained context length is 128K tokens. The repository has 2 quant files, from 13.1 GB (Q5_K_M) to 19.7 GB (Q8_0).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q5_K_M | 13.1 GB | 16.3 GB | Too big | Get file → | |
| Q8_0 | 19.7 GB | 22.9 GB | Too big | Get file → |
What GPU do you need for RainbowsEdge-v0.1-rc1-18B?
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 Q8_0 (19.7 GB file, about 22.9 GB in use).
Which RainbowsEdge-v0.1-rc1-18B quant should you choose?
Q5_K_M (13.1 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
Frequently asked questions about RainbowsEdge-v0.1-rc1-18B
How much VRAM does RainbowsEdge-v0.1-rc1-18B need?
About 16.3 GB at Q5_K_M with an 8K context window. That is the 13.1 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 RainbowsEdge-v0.1-rc1-18B on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 16.3 GB, so you would need a larger GPU or CPU offloading.
What is the file size of RainbowsEdge-v0.1-rc1-18B GGUF?
It depends on the quant: Q5_K_M is 13.1 GB, Q8_0 is 19.7 GB.
What context length does RainbowsEdge-v0.1-rc1-18B support?
The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 2.7 GB at 8K and 10.7 GB at 32K.
Where can I download RainbowsEdge-v0.1-rc1-18B GGUF?
The files are on Hugging Face in the invisietch/RainbowsEdge-v0.1-rc1-18B-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 RainbowsEdge-v0.1-rc1-18B use?
Hugging Face lists the license as llama3. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.