JiRackDeltaNet_27b needs about 9.7 GB of memory at TQ1_0 (a 7.0 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 2 quants, from 7.0 GB (TQ1_0) to 8.2 GB (TQ2_0). Longer context needs more: at 32K tokens the KV cache alone adds about 8.7 GB.
JiRackDeltaNet_27b is a 27.3B-parameter Jirackdeltanet model in GGUF format, quantized by mradermacher. Its trained context length is 256K tokens. The repository has 2 quant files, from 7.0 GB (TQ1_0) to 8.2 GB (TQ2_0).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| TQ1_0 | 7.0 GB | 9.7 GB | Too big | Get file → | |
| TQ2_0 | 8.2 GB | 10.8 GB | Too big | Get file → |
What GPU do you need for JiRackDeltaNet_27b?
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 TQ2_0 (8.2 GB file, about 10.8 GB in use).
Which JiRackDeltaNet_27b quant should you choose?
TQ1_0 (7.0 GB) is the middle option in this repository. Lower bit counts mean smaller files and more quality loss.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about JiRackDeltaNet_27b
How much VRAM does JiRackDeltaNet_27b need?
About 9.7 GB at TQ1_0 with an 8K context window. That is the 7.0 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 JiRackDeltaNet_27b on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 9.7 GB, so you would need a larger GPU or CPU offloading.
What is the file size of JiRackDeltaNet_27b GGUF?
It depends on the quant: TQ1_0 is 7.0 GB, TQ2_0 is 8.2 GB.
What context length does JiRackDeltaNet_27b support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 2.2 GB at 8K and 8.7 GB at 32K.
Where can I download JiRackDeltaNet_27b GGUF?
The files are on Hugging Face in the mradermacher/JiRackDeltaNet_27b-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 JiRackDeltaNet_27b use?
Hugging Face lists the license as mit. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.