kappa_20b_131k needs about 16.7 GB of memory at Q4_K_M (a 15.8 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 25 quants, from 0.0 GB to 22.2 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 1.6 GB.
kappa_20b_131k – 20.9B MoE LLM with 131K context and tool‑calling
kappa_20b_131k is a full‑parameter SFT on a 20.9B MoE base. It supports 131072 context tokens and tool calling. The model was trained on 9 personas and runs on llama.cpp.
Good at
- Tool calling
- Long‑context 131K
- Persona‑conditioned dialogue
Limits
- No vision support
- License is other
- Large VRAM requirement
Best for
- Multi‑turn conversations
- Tool‑enabled workflows
- Persona‑driven content
Who it’s for. Developers building conversational agents that need long context and tool integration. Researchers exploring persona conditioning on a MoE backbone.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.0 GB | 0.9 GB | Fits | Get file → | |
| IQ1_M | 12.0 GB | 12.9 GB | Too big | Get file → | |
| IQ1_S | 12.0 GB | 12.9 GB | Too big | Get file → | |
| IQ2_XXS | 12.0 GB | 12.9 GB | Too big | Get file → | |
| IQ2_XS | 12.0 GB | 12.9 GB | Too big | Get file → | |
| Q3_K_S | 12.1 GB | 13.0 GB | Too big | Get file → | |
| IQ2_M | 12.1 GB | 13.0 GB | Too big | Get file → | |
| IQ2_S | 12.1 GB | 13.0 GB | Too big | Get file → | |
| IQ3_S | 12.1 GB | 13.0 GB | Too big | Get file → | |
| IQ3_XS | 12.1 GB | 13.0 GB | Too big | Get file → | |
| IQ3_XXS | 12.1 GB | 13.0 GB | Too big | Get file → | |
| Q2_K | 12.1 GB | 13.0 GB | Too big | Get file → | |
| IQ4_XS | 12.1 GB | 13.0 GB | Too big | Get file → | |
| MXFP4_MOE | 12.1 GB | 13.0 GB | Too big | Get file → | |
| Q2_K_S | 12.1 GB | 13.0 GB | Too big | Get file → | |
| Q4_0 | 12.1 GB | 13.1 GB | Too big | Get file → | |
| IQ3_M | 12.2 GB | 13.1 GB | Too big | Get file → | |
| Q3_K_M | 12.9 GB | 13.8 GB | Too big | Get file → | |
| Q3_K_L | 13.3 GB | 14.2 GB | Too big | Get file → | |
| Q4_1 | 13.4 GB | 14.3 GB | Too big | Get file → | |
| Q4_K_S | 14.7 GB | 15.6 GB | Too big | Get file → | |
| Q4_K_M | 15.8 GB | 16.7 GB | Too big | Get file → | |
| Q5_K_S | 15.9 GB | 16.8 GB | Too big | Get file → | |
| Q5_K_M | 16.9 GB | 17.8 GB | Too big | Get file → | |
| Q6_K | 22.2 GB | 23.1 GB | Too big | Get file → |
For 8‑GB VRAM use IQ1_M or IQ1_S (12.02 GB file, ~12.9 GB memory). For 12‑GB VRAM use Q2_K or IQ2_XS (12.07 GB file, ~13 GB memory). For 16‑GB VRAM use Q4_0 or IQ3_M (12.15 GB file, ~13.1 GB memory).
What GPU do you need for kappa_20b_131k?
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: the best quant that fits is the main file (0.0 GB file, about 0.9 GB in use).
- 6 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 0.9 GB in use).
- 8 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 0.9 GB in use).
- 12 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 0.9 GB in use).
- 16 GB VRAM: the best quant that fits is Q4_K_S (14.7 GB file, about 15.6 GB in use).
- 24 GB VRAM: the best quant that fits is Q6_K (22.2 GB file, about 23.1 GB in use).
Which kappa_20b_131k quant should you choose?
Q4_K_M is the usual starting point for kappa_20b_131k: it balances file size and quality well. Here it is a 15.8 GB file.
If memory is tight, the smallest file is the first one in the table at 0.0 GB, with the quality trade-offs that come with fewer bits.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about kappa_20b_131k
How much VRAM does kappa_20b_131k need?
About 16.7 GB at Q4_K_M with an 8K context window. That is the 15.8 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 kappa_20b_131k on an 8 GB GPU?
Yes, with the smaller files: the 0.0 GB file needs about 0.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of kappa_20b_131k GGUF?
It depends on the quant: file is 0.0 GB, IQ1_M is 12.0 GB, IQ1_S is 12.0 GB, IQ2_XXS is 12.0 GB, IQ2_XS is 12.0 GB, Q3_K_S is 12.1 GB and 19 more.
What context length does kappa_20b_131k support?
The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 0.4 GB at 8K and 1.6 GB at 32K.
Where can I download kappa_20b_131k GGUF?
The files are on Hugging Face in the mradermacher/kappa-20b-131k-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 kappa_20b_131k use?
Hugging Face lists the license as other. 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 kappa_20b_131k on 8 GB VRAM?
Use IQ1_M or IQ1_S quant, which are 12.02 GB files and require about 12.9 GB memory at 8K context.
Does the model support vision?
No, the model has no vision capability.
What context length does it support?
It supports 131072 tokens, as trained.