Mixnu i1 needs about 16.8 GB of memory at Q4_K_M (a 12.0 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 16 quants, from 6.7 GB (IQ2_M) to 16.3 GB (Q6_K).
Mixnu i1 – 19.8B Korean LLM with Mixture of Experts
Mixnu i1 is a 19.8B parameter Korean large language model built with a Mixture of Experts architecture. It uses an extended Llama‑2 tokenizer and supports a 4096 token context window. The model is released under the Apache‑2.0 license.
Good at
- Korean language generation
- Domain‑specific knowledge (medicine, law, finance)
- Consistent style across prompts
Limits
- No vision support
- Requires large VRAM for higher‑quality quants
- No explicit language list beyond Korean
Best for
- Chatbots in Korean
- Domain‑specific Korean content creation
- Research prototyping with Korean data
Who it’s for. Developers and researchers needing a Korean LLM with expert specialization. The model is suitable for applications that require nuanced Korean language understanding and domain knowledge.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ2_M | 6.7 GB | 9.4 GB | Too big | Get file → | |
| Q2_K | 7.3 GB | 10.0 GB | Too big | Get file → | |
| IQ3_XXS | 7.6 GB | 10.3 GB | Too big | Get file → | |
| IQ3_XS | 8.1 GB | 10.8 GB | Too big | Get file → | |
| IQ3_S | 8.6 GB | 11.3 GB | Too big | Get file → | |
| Q3_K_S | 8.6 GB | 11.3 GB | Too big | Get file → | |
| IQ3_M | 8.8 GB | 11.5 GB | Too big | Get file → | |
| Q3_K_M | 9.6 GB | 12.2 GB | Too big | Get file → | |
| Q3_K_L | 10.4 GB | 13.0 GB | Too big | Get file → | |
| IQ4_XS | 10.6 GB | 13.2 GB | Too big | Get file → | |
| Q4_0 | 11.3 GB | 13.9 GB | Too big | Get file → | |
| Q4_K_S | 11.3 GB | 14.0 GB | Too big | Get file → | |
| Q4_K_M | 12.0 GB | 14.7 GB | Too big | Get file → | |
| Q5_K_S | 13.7 GB | 16.3 GB | Too big | Get file → | |
| Q5_K_M | 14.1 GB | 16.7 GB | Too big | Get file → | |
| Q6_K | 16.3 GB | 18.9 GB | Too big | Get file → |
For 8‑GB VRAM, use IQ2_M (6.72 GB, 11.5 GB memory). For 12‑GB VRAM, use Q3_K_S (8.6 GB, 13.4 GB memory). For 16‑GB VRAM, use Q4_K_M (12.03 GB, 16.8 GB memory). Estimates are approximate.
What GPU do you need for Mixnu i1?
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 IQ2_M (6.7 GB file, about 11.5 GB in use).
- 16 GB VRAM: the best quant that fits is IQ4_XS (10.6 GB file, about 15.4 GB in use).
- 24 GB VRAM: the best quant that fits is Q6_K (16.3 GB file, about 21.1 GB in use).
Which Mixnu i1 quant should you choose?
Q4_K_M is the usual starting point for Mixnu i1: it balances file size and quality well. Here it is a 12.0 GB file.
If memory is tight, the smallest file is IQ2_M at 6.7 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 Mixnu i1
How much VRAM does Mixnu i1 need?
About 16.8 GB at Q4_K_M with an 8K context window. That is the 12.0 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 Mixnu i1 on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 11.5 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Mixnu i1 GGUF?
It depends on the quant: IQ2_M is 6.7 GB, Q2_K is 7.3 GB, IQ3_XXS is 7.6 GB, IQ3_XS is 8.1 GB, IQ3_S is 8.6 GB, Q3_K_S is 8.6 GB and 10 more.
What context length does Mixnu i1 support?
The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 4.3 GB at 8K and 2.1 GB at 4K.
Where can I download Mixnu i1 GGUF?
The files are on Hugging Face in the mradermacher/Mixnu-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 Mixnu i1 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 Mixnu i1 on 8 GB VRAM?
Use the IQ2_M quant, which is 6.72 GB and requires about 11.5 GB of VRAM at 8k context.
Does Mixnu i1 support English?
The model was evaluated on English but is primarily Korean; English support is limited.
Is Mixnu i1 free to use?
Yes, it is released under the Apache‑2.0 license, allowing free use and modification.