Knight Miqu 27B MoE needs about 18.3 GB of memory at Q4_K_M (a 16.8 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 14 quants, from 10.3 GB (Q2_K) to 29.7 GB (Q8_0).
Knight Miqu 27B MoE – 27.9B llama model in GGUF format
Knight Miqu 27B MoE is a 27.9B parameter llama model available in multiple GGUF quantizations. It supports a context length of 32764 tokens and is released under the apache-2.0 license. The model is provided by mradermacher and can be used with llama.cpp.
Good at
- Large context handling
- High parameter count
- Apache-2.0 licensed
Limits
- No mixture of experts
- Limited to text only
- Requires 8k context for memory estimates
Best for
- Long-form content generation
- Complex reasoning tasks
- Large context summarization
Who it’s for. Developers and researchers needing a large llama model for text generation. The model is suitable for local deployment with sufficient VRAM and RAM to accommodate the chosen quantization.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 10.3 GB | 11.9 GB | Too big | Get file → | |
| IQ3_XS | 11.5 GB | 13.1 GB | Too big | Get file → | |
| Q3_K_S | 12.1 GB | 13.7 GB | Too big | Get file → | |
| IQ3_S | 12.1 GB | 13.7 GB | Too big | Get file → | |
| IQ3_M | 12.5 GB | 14.1 GB | Too big | Get file → | |
| Q3_K_M | 13.5 GB | 15.0 GB | Too big | Get file → | |
| Q3_K_L | 14.7 GB | 16.2 GB | Too big | Get file → | |
| IQ4_XS | 15.1 GB | 16.7 GB | Too big | Get file → | |
| Q4_K_S | 15.9 GB | 17.5 GB | Too big | Get file → | |
| Q4_K_M | 16.8 GB | 18.3 GB | Too big | Get file → | |
| Q5_K_S | 19.2 GB | 20.8 GB | Too big | Get file → | |
| Q5_K_M | 19.7 GB | 21.3 GB | Too big | Get file → | |
| Q6_K | 22.9 GB | 24.5 GB | Too big | Get file → | |
| Q8_0 | 29.7 GB | 31.2 GB | Too big | Get file → |
For 8‑GB VRAM, use Q2_K (file size 10.33 GB, estimated memory 11.9 GB). For 12‑GB VRAM, Q3_K_S (12.1 GB, 13.7 GB) or IQ3_S (12.13 GB, 13.7 GB). For 16‑GB VRAM, Q4_K_M (16.77 GB, 18.3 GB) or Q5_K_S (19.22 GB, 20.8 GB). Estimates are approximate.
What GPU do you need for Knight Miqu 27B MoE?
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 (10.3 GB file, about 11.9 GB in use).
- 16 GB VRAM: the best quant that fits is Q3_K_M (13.5 GB file, about 15.0 GB in use).
- 24 GB VRAM: the best quant that fits is Q5_K_M (19.7 GB file, about 21.3 GB in use).
- 32 GB VRAM: the best quant that fits is Q8_0 (29.7 GB file, about 31.2 GB in use).
Which Knight Miqu 27B MoE quant should you choose?
Q4_K_M is the usual starting point for Knight Miqu 27B MoE: it balances file size and quality well. Here it is a 16.8 GB file.
The Q8_0 file is 29.7 GB, about 1.8 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 10.3 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 Knight Miqu 27B MoE
How much VRAM does Knight Miqu 27B MoE need?
About 18.3 GB at Q4_K_M with an 8K context window. That is the 16.8 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 Knight Miqu 27B MoE on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 11.9 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Knight Miqu 27B MoE GGUF?
It depends on the quant: Q2_K is 10.3 GB, IQ3_XS is 11.5 GB, Q3_K_S is 12.1 GB, IQ3_S is 12.1 GB, IQ3_M is 12.5 GB, Q3_K_M is 13.5 GB and 8 more.
What context length does Knight Miqu 27B MoE support?
The GGUF header lists a trained context length of 32,764 tokens (32K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.3 GB at 32K.
Where can I download Knight Miqu 27B MoE GGUF?
The files are on Hugging Face in the mradermacher/Knight-Miqu-27B-MoE-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 Knight Miqu 27B MoE 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 Knight Miqu 27B MoE on 8 GB VRAM?
Use the Q2_K quant, which requires about 11.9 GB of VRAM at 8k context. It may exceed 8 GB, so a higher VRAM GPU is recommended.
What context length does the model support?
The model was trained with a context length of 32764 tokens.
Is the model licensed for commercial use?
Yes, it is released under the apache-2.0 license, which permits commercial use.