Keural Nova v1.1 needs about 22.9 GB of memory at Q4_K_M (a 21.7 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 11 quants, from 13.2 GB (Q2_K) to 37.8 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 2.8 GB.
Keural Nova v1.1 – 35.5B parameter Qwen35moe Mixture‑of‑Experts model
Keural Nova v1.1 is a Korean‑focused instruction‑tuned model built on Qwen/Qwen3.6‑35B‑A3B. It is a 35.5B parameter Mixture‑of‑Experts model with ~3B active parameters per token. The fine‑tune improves Korean conversational quality and answer formatting.
Good at
- Korean dialogue and comprehension
- Instruction following
- Answer formatting
Limits
- Limited to 262144 context tokens
- No vision support
- License is Apache‑2.0
Best for
- Korean conversational agents
- Korean language tutoring
- Chatbot integration
Who it’s for. Developers building Korean‑centric chatbots or educational tools. The model is suitable for applications that require high‑quality Korean dialogue and instruction following.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 13.2 GB | 14.4 GB | Too big | Get file → | |
| Q3_K_S | 15.5 GB | 16.7 GB | Too big | Get file → | |
| Q3_K_M | 17.2 GB | 18.4 GB | Too big | Get file → | |
| Q3_K_L | 18.6 GB | 19.7 GB | Too big | Get file → | |
| IQ4_XS | 19.4 GB | 20.6 GB | Too big | Get file → | |
| Q4_K_S | 20.4 GB | 21.6 GB | Too big | Get file → | |
| Q4_K_M | 21.7 GB | 22.9 GB | Too big | Get file → | |
| Q5_K_S | 24.6 GB | 25.8 GB | Too big | Get file → | |
| Q5_K_M | 25.3 GB | 26.5 GB | Too big | Get file → | |
| Q6_K | 29.2 GB | 30.4 GB | Too big | Get file → | |
| Q8_0 | 37.8 GB | 39.0 GB | Too big | Get file → |
For 8 GB VRAM, use Q4_K_M (file size 21.71 GB, estimated memory 22.9 GB). For 16 GB VRAM, Q5_K_M (file size 25.35 GB, estimated memory 26.5 GB) is a good balance. For larger budgets, Q8_0 (file size 37.8 GB, estimated memory 39 GB) offers the highest fidelity.
What GPU do you need for Keural Nova v1.1?
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: the best quant that fits is Q2_K (13.2 GB file, about 14.4 GB in use).
- 24 GB VRAM: the best quant that fits is Q4_K_M (21.7 GB file, about 22.9 GB in use).
- 32 GB VRAM: the best quant that fits is Q6_K (29.2 GB file, about 30.4 GB in use).
- 48 GB VRAM: the best quant that fits is Q8_0 (37.8 GB file, about 39.0 GB in use).
Which Keural Nova v1.1 quant should you choose?
Q4_K_M is the usual starting point for Keural Nova v1.1: it balances file size and quality well. Here it is a 21.7 GB file.
The Q8_0 file is 37.8 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 13.2 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 Keural Nova v1.1
How much VRAM does Keural Nova v1.1 need?
About 22.9 GB at Q4_K_M with an 8K context window. That is the 21.7 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 Keural Nova v1.1 on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 14.4 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Keural Nova v1.1 GGUF?
It depends on the quant: Q2_K is 13.2 GB, Q3_K_S is 15.5 GB, Q3_K_M is 17.2 GB, Q3_K_L is 18.6 GB, IQ4_XS is 19.4 GB, Q4_K_S is 20.4 GB and 5 more.
What context length does Keural Nova v1.1 support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 0.7 GB at 8K and 2.8 GB at 32K.
Where can I download Keural Nova v1.1 GGUF?
The files are on Hugging Face in the mradermacher/Keural-Nova-v1.1-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 Keural Nova v1.1 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 Keural Nova v1.1 on 8 GB VRAM?
Use the Q4_K_M quant; it requires about 22.9 GB of VRAM at 8k context, so 8 GB is insufficient.
Does this model support vision tasks?
No, the model does not have vision capabilities.
What license applies to this model?
The model is released under the Apache‑2.0 license.