Shisa v2 Mistral Small 24b 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 11 quants, from 8.9 GB (Q2_K) to 25.1 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 5.4 GB.
Shisa v2 Mistral Small 24b – 23.6B parameter bilingual Japanese/English chat model
Shisa v2 Mistral Small 24b is a 23.6B parameter model optimized for Japanese and English. It is trained on the Shisa V2 dataset and uses the llama architecture. The model supports a 32768 token context window and is released under Apache‑2.0.
Good at
- Japanese language tasks
- English general‑purpose chat
- Large context handling
Limits
- No vision support
- Requires 8K context for memory estimates
- No mixture of experts
Best for
- Japanese content creation
- Multilingual chatbots
- Long‑form text generation
Who it’s for. Developers building bilingual chat applications or content tools that require robust Japanese and English support. The model is suitable for users who need a large context window and are comfortable with open‑source licensing.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 8.9 GB | 10.7 GB | Too big | Get file → | |
| Q3_K_S | 10.4 GB | 12.2 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 | 12.9 GB | 14.7 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 → | |
| 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 → | |
| Q8_0 | 25.1 GB | 26.9 GB | Too big | Get file → |
For 8‑GB VRAM use Q2_K (8.89 GB, ~10.7 GB memory at 8K context). For 12‑GB VRAM use Q3_K_S (10.4 GB, ~12.2 GB memory). For 16‑GB VRAM use Q4_K_M (14.33 GB, ~16.2 GB memory). Memory estimates are approximate.
What GPU do you need for Shisa v2 Mistral Small 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: the best quant that fits is Q2_K (8.9 GB file, about 10.7 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).
- 32 GB VRAM: the best quant that fits is Q8_0 (25.1 GB file, about 26.9 GB in use).
Which Shisa v2 Mistral Small 24b quant should you choose?
Q4_K_M is the usual starting point for Shisa v2 Mistral Small 24b: it balances file size and quality well. Here it is a 14.3 GB file.
The Q8_0 file is 25.1 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 Q2_K at 8.9 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Shisa v2 Mistral Small 24b
How much VRAM does Shisa v2 Mistral Small 24b 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 Shisa v2 Mistral Small 24b on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 10.7 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Shisa v2 Mistral Small 24b GGUF?
It depends on the quant: Q2_K is 8.9 GB, Q3_K_S is 10.4 GB, Q3_K_M is 11.5 GB, Q3_K_L is 12.4 GB, IQ4_XS is 12.9 GB, Q4_K_S is 13.5 GB and 5 more.
What context length does Shisa v2 Mistral Small 24b 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 Shisa v2 Mistral Small 24b GGUF?
The files are on Hugging Face in the mradermacher/shisa-v2-mistral-small-24b-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 Shisa v2 Mistral Small 24b 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 Shisa v2 Mistral Small 24b on 8 GB VRAM?
Yes, the Q2_K quant is 8.89 GB and requires about 10.7 GB of VRAM at 8K context.
Does this model support image input?
No, the model does not have vision capabilities.
What license applies to this model?
The model is released under the Apache‑2.0 license.