POCKET KR 96 needs about 9.7 GB of memory at Q2_K (a 8.5 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 3 quants, from 5.1 GB (IQ2_M) to 11.0 GB (Q3_K_M). Longer context needs more: at 32K tokens the KV cache alone adds about 2.7 GB.
POCKET KR 96 is a 22.6B-parameter Darwin model in GGUF format, quantized by FINAL-Bench. Its trained context length is 256K tokens. The repository has 3 quant files, from 5.1 GB (IQ2_M) to 11.0 GB (Q3_K_M).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ2_M | 5.1 GB | 6.3 GB | Fits | Get file → | |
| Q2_K | 8.5 GB | 9.7 GB | Too big | Get file → | |
| Q3_K_M | 11.0 GB | 12.2 GB | Too big | Get file → |
What GPU do you need for POCKET KR 96?
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: the best quant that fits is IQ2_M (5.1 GB file, about 6.3 GB in use).
- 12 GB VRAM: the best quant that fits is Q2_K (8.5 GB file, about 9.7 GB in use).
- 16 GB VRAM: the best quant that fits is Q3_K_M (11.0 GB file, about 12.2 GB in use).
Which POCKET KR 96 quant should you choose?
Q2_K (8.5 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 IQ2_M at 5.1 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 POCKET KR 96
How much VRAM does POCKET KR 96 need?
About 9.7 GB at Q2_K with an 8K context window. That is the 8.5 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 POCKET KR 96 on an 8 GB GPU?
Yes, with IQ2_M: the 5.1 GB file needs about 6.3 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of POCKET KR 96 GGUF?
It depends on the quant: IQ2_M is 5.1 GB, Q2_K is 8.5 GB, Q3_K_M is 11.0 GB.
What context length does POCKET KR 96 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 2.7 GB at 32K.
Where can I download POCKET KR 96 GGUF?
The files are on Hugging Face in the FINAL-Bench/POCKET-KR-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 POCKET KR 96 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.