Sakura-24B-Spice needs about 16.2 GB of memory at Q4_K_M (a 14.3 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 24 quants, from 0.0 GB to 19.3 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 5.4 GB.
Sakura-24B-Spice – a 23.6B‑parameter Llama model focused on roleplay
Sakura-24B-Spice is a 23.6‑billion‑parameter Llama model built on the Mistral‑Small‑2501 architecture. It merges three source models using DARE‑TIES to create a volatile, creative persona. The model supports a 32,768‑token context window and is released under Apache‑2.0.
Good at
- Intense roleplay with complex characters
- Unpredictable narrative twists
- High‑density logical reasoning
Limits
- No vision support
- Requires large VRAM for higher‑quality quants
- License is Apache‑2.0
Best for
- Roleplaying games with deep NPCs
- Dynamic storytelling in text adventures
- Adversarial AI scenarios
Who it’s for. Developers and hobbyists who need a large, roleplay‑oriented model with a cynical, unfiltered personality. The model is suitable for projects that can handle its memory demands and do not require vision capabilities.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.0 GB | 1.9 GB | Fits | Get file → | |
| IQ1_S | 5.3 GB | 7.1 GB | Fits | Get file → | |
| IQ1_M | 5.8 GB | 7.6 GB | Tight | Get file → | |
| IQ2_XXS | 6.5 GB | 8.4 GB | Too big | Get file → | |
| IQ2_XS | 7.2 GB | 9.0 GB | Too big | Get file → | |
| IQ2_S | 7.5 GB | 9.3 GB | Too big | Get file → | |
| IQ2_M | 8.1 GB | 10.0 GB | Too big | Get file → | |
| Q2_K_S | 8.3 GB | 10.2 GB | Too big | Get file → | |
| Q2_K | 8.9 GB | 10.7 GB | Too big | Get file → | |
| IQ3_XXS | 9.3 GB | 11.1 GB | Too big | Get file → | |
| IQ3_XS | 9.9 GB | 11.7 GB | Too big | Get file → | |
| Q3_K_S | 10.4 GB | 12.2 GB | Too big | Get file → | |
| IQ3_S | 10.4 GB | 12.3 GB | Too big | Get file → | |
| IQ3_M | 10.7 GB | 12.5 GB | Too big | Get file → | |
| Q3_K_M | 11.5 GB | 13.3 GB | Too big | Get file → | |
| Q3_K_L | 12.4 GB | 14.2 GB | Too big | Get file → | |
| IQ4_XS | 12.8 GB | 14.6 GB | Too big | Get file → | |
| Q4_0 | 13.5 GB | 15.3 GB | Too big | Get file → | |
| Q4_K_S | 13.5 GB | 15.4 GB | Too big | Get file → | |
| Q4_K_M | 14.3 GB | 16.2 GB | Too big | Get file → | |
| Q4_1 | 14.9 GB | 16.7 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 → | |
| Q6_K | 19.3 GB | 21.2 GB | Too big | Get file → |
For 8 GB VRAM, use IQ1_S (5.27 GB, 7.1 GB memory at 8k context) or IQ1_M (5.75 GB, 7.6 GB). With 12 GB VRAM, IQ2_XXS (6.55 GB, 8.4 GB) or IQ2_XS (7.21 GB, 9 GB) are suitable. For 16 GB VRAM, Q4_0 (13.49 GB, 15.3 GB) or Q4_K_M (14.33 GB, 16.2 GB) provide a balance of size and performance.
What GPU do you need for Sakura-24B-Spice?
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 the main file (0.0 GB file, about 1.9 GB in use).
- 6 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 1.9 GB in use).
- 8 GB VRAM: the best quant that fits is IQ1_M (5.8 GB file, about 7.6 GB in use).
- 12 GB VRAM: the best quant that fits is IQ3_XS (9.9 GB file, about 11.7 GB in use).
- 16 GB VRAM: the best quant that fits is Q4_K_S (13.5 GB file, about 15.4 GB in use).
- 24 GB VRAM: the best quant that fits is Q6_K (19.3 GB file, about 21.2 GB in use).
Which Sakura-24B-Spice quant should you choose?
Q4_K_M is the usual starting point for Sakura-24B-Spice: it balances file size and quality well. Here it is a 14.3 GB file.
If memory is tight, the smallest file is the first one in the table at 0.0 GB, with the quality trade-offs that come with fewer bits.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Sakura-24B-Spice
How much VRAM does Sakura-24B-Spice need?
About 16.2 GB at Q4_K_M with an 8K context window. That is the 14.3 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 Sakura-24B-Spice on an 8 GB GPU?
Yes, with IQ1_M: the 5.8 GB file needs about 7.6 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Sakura-24B-Spice GGUF?
It depends on the quant: file is 0.0 GB, IQ1_S is 5.3 GB, IQ1_M is 5.8 GB, IQ2_XXS is 6.5 GB, IQ2_XS is 7.2 GB, IQ2_S is 7.5 GB and 18 more.
What context length does Sakura-24B-Spice support?
The GGUF header lists a trained context length of 32,768 tokens (32K). 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 Sakura-24B-Spice GGUF?
The files are on Hugging Face in the mradermacher/Sakura-24B-Spice-i1-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 Sakura-24B-Spice 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.
Can I run Sakura-24B-Spice on 8 GB VRAM?
Yes, using IQ1_S or IQ1_M quantizations which require about 7–7.6 GB memory at 8k context.
Does the model support image inputs?
No, Sakura-24B-Spice does not have vision capabilities.
What license applies to this model?
The model is released under the Apache‑2.0 license.