RP Spectrum 24B needs about 21.2 GB of memory at Q6_K (a 19.3 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 11 quants, from 16.3 GB (Q5_0) to 47.2 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 5.4 GB.
RP Spectrum 24B is a 23.6B-parameter Spectrum model in GGUF format, quantized by Casual-Autopsy. Its trained context length is 128K tokens. The repository has 11 quant files, from 16.3 GB (Q5_0) to 47.2 GB (BF16).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q5_0 | 16.3 GB | 18.1 GB | Too big | Get file → | |
| Q5_K_S | 16.3 GB | 18.1 GB | Too big | Get file → | |
| Q5_K_M | 16.8 GB | 18.6 GB | Too big | Get file → | |
| Q5_K_L | 17.2 GB | 19.0 GB | Too big | Get file → | |
| Q5_1 | 17.7 GB | 19.6 GB | Too big | Get file → | |
| Q6_K | 19.3 GB | 21.2 GB | Too big | Get file → | |
| Q6_K_L | 19.7 GB | 21.5 GB | Too big | Get file → | |
| Q6_K | 20.9 GB | 22.8 GB | Too big | Get file → | |
| Q8_0 | 25.1 GB | 26.9 GB | Too big | Get file → | |
| Q8_0 | 26.3 GB | 28.2 GB | Too big | Get file → | |
| BF16 | 47.2 GB | 49.0 GB | Too big | Get file → |
What GPU do you need for RP Spectrum 24B?
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 Q6_K (20.9 GB file, about 22.8 GB in use).
- 32 GB VRAM: the best quant that fits is Q8_0 (26.3 GB file, about 28.2 GB in use).
- 48 GB VRAM: the best quant that fits is Q8_0 (26.3 GB file, about 28.2 GB in use).
Which RP Spectrum 24B quant should you choose?
Q6_K (19.3 GB) is the middle option in this repository. Very close to the original quality for most uses, at a clearly larger size than 4-bit.
If memory is tight, the smallest file is Q5_0 at 16.3 GB, with the quality trade-offs that come with fewer bits. 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 RP Spectrum 24B
How much VRAM does RP Spectrum 24B need?
About 21.2 GB at Q6_K with an 8K context window. That is the 19.3 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 RP Spectrum 24B on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 18.1 GB, so you would need a larger GPU or CPU offloading.
What is the file size of RP Spectrum 24B GGUF?
It depends on the quant: Q5_0 is 16.3 GB, Q5_K_S is 16.3 GB, Q5_K_M is 16.8 GB, Q5_K_L is 17.2 GB, Q5_1 is 17.7 GB, Q6_K is 19.3 GB and 5 more.
What context length does RP Spectrum 24B support?
The GGUF header lists a trained context length of 131,072 tokens (128K). 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 RP Spectrum 24B GGUF?
The files are on Hugging Face in the Casual-Autopsy/RP-Spectrum-24B-static-GGUFs repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.