lightblue Karasu Mixtral 8x22B v0.1 needs about 40.3 GB of memory at IQ2_XXS (a 37.9 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 6 quants, from 29.6 GB (IQ1_S) to 46.7 GB (IQ2_M). Longer context needs more: at 32K tokens the KV cache alone adds about 7.5 GB.
lightblue Karasu Mixtral 8x22B v0.1 – 141B parameter Mistral model in GGUF format
lightblue Karasu Mixtral 8x22B v0.1 is a 141B parameter Mistral model converted to GGUF. It supports a 65536 token context and is licensed under Apache‑2.0. The model is available in several quantizations for different memory budgets.
Good at
- Large context handling
- Japanese language support
- Mixture of experts architecture
Limits
- No vision support
- Requires high VRAM for larger quants
- No explicit language list beyond en and ja
Best for
- Long‑form content generation
- Japanese text processing
- Research prototyping
Who it’s for. Developers and researchers needing a large‑context LLM with Japanese language capabilities. The model is suitable for those who can allocate sufficient GPU memory and prefer open‑source licensing.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ1_S | 29.6 GB | 32.0 GB | Too big | Get file → | |
| IQ1_M | 32.7 GB | 35.1 GB | Too big | Get file → | |
| IQ2_XXS | 37.9 GB | 40.3 GB | Too big | Get file → | |
| IQ2_XS | 42.0 GB | 44.4 GB | Too big | Get file → | |
| IQ2_S | 42.6 GB | 45.0 GB | Too big | Get file → | |
| IQ2_M | 46.7 GB | 49.1 GB | Too big | Get file → |
For 8 GB VRAM use IQ1_S (29.64 GB file, ~32 GB memory at 8k context). For 12 GB VRAM use IQ1_M (32.73 GB file, ~35.1 GB memory). For 16 GB VRAM use IQ2_XXS (37.88 GB file, ~40.3 GB memory). Estimates are approximate.
What GPU do you need for lightblue Karasu Mixtral 8x22B v0.1?
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: no quant fits at an 8K context.
- 32 GB VRAM: the best quant that fits is IQ1_S (29.6 GB file, about 32.0 GB in use).
- 48 GB VRAM: the best quant that fits is IQ2_S (42.6 GB file, about 45.0 GB in use).
Which lightblue Karasu Mixtral 8x22B v0.1 quant should you choose?
IQ2_XXS (37.9 GB) is the middle option in this repository. 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.
If memory is tight, the smallest file is IQ1_S at 29.6 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
Frequently asked questions about lightblue Karasu Mixtral 8x22B v0.1
How much VRAM does lightblue Karasu Mixtral 8x22B v0.1 need?
About 40.3 GB at IQ2_XXS with an 8K context window. That is the 37.9 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 lightblue Karasu Mixtral 8x22B v0.1 on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 32.0 GB, so you would need a larger GPU or CPU offloading.
What is the file size of lightblue Karasu Mixtral 8x22B v0.1 GGUF?
It depends on the quant: IQ1_S is 29.6 GB, IQ1_M is 32.7 GB, IQ2_XXS is 37.9 GB, IQ2_XS is 42.0 GB, IQ2_S is 42.6 GB, IQ2_M is 46.7 GB.
What context length does lightblue Karasu Mixtral 8x22B v0.1 support?
The GGUF header lists a trained context length of 65,536 tokens (64K). The KV cache grows with the context you use: about 1.9 GB at 8K and 7.5 GB at 32K.
Where can I download lightblue Karasu Mixtral 8x22B v0.1 GGUF?
The files are on Hugging Face in the mmnga/lightblue-Karasu-Mixtral-8x22B-v0.1-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 lightblue Karasu Mixtral 8x22B v0.1 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 this model on 8 GB VRAM?
Use the IQ1_S quantization; it requires about 32 GB of VRAM at 8k context, which exceeds 8 GB, so it is not feasible.
Does this model support Japanese?
Yes, it was trained with TFMC/imatrix-dataset-for-japanese-llm and includes Japanese language support.
What license applies to this model?
The model is released under the Apache‑2.0 license.