JiRackDeltaNet 70b needs about 47.5 GB of memory at Q4_K_M (a 42.7 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 3 quants, from 33.9 GB (Q3_K_M) to 57.4 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 17.3 GB.
JiRackDeltaNet 70b is a 69.9B-parameter Jirackdeltanet model in GGUF format, quantized by CMSManhattan. Its trained context length is 256K tokens. The repository has 3 quant files, from 33.9 GB (Q3_K_M) to 57.4 GB (Q6_K).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q3_K_M | 33.9 GB | 38.7 GB | Too big | Get file → | |
| Q4_K_M | 42.7 GB | 47.5 GB | Too big | Get file → | |
| Q6_K | 57.4 GB (2 parts) | 62.2 GB | Too big | Get file → |
What GPU do you need for JiRackDeltaNet 70b?
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: no quant fits at an 8K context.
- 24 GB VRAM: no quant fits at an 8K context.
- 32 GB VRAM: no quant fits at an 8K context.
- 48 GB VRAM: the best quant that fits is Q4_K_M (42.7 GB file, about 47.5 GB in use).
Which JiRackDeltaNet 70b quant should you choose?
Q4_K_M is the usual starting point for JiRackDeltaNet 70b: it balances file size and quality well. Here it is a 42.7 GB file.
If memory is tight, the smallest file is Q3_K_M at 33.9 GB, with the quality trade-offs that come with fewer bits. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about JiRackDeltaNet 70b
How much VRAM does JiRackDeltaNet 70b need?
About 47.5 GB at Q4_K_M with an 8K context window. That is the 42.7 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 JiRackDeltaNet 70b on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 38.7 GB, so you would need a larger GPU or CPU offloading.
What is the file size of JiRackDeltaNet 70b GGUF?
It depends on the quant: Q3_K_M is 33.9 GB, Q4_K_M is 42.7 GB, Q6_K is 57.4 GB.
What context length does JiRackDeltaNet 70b support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 4.3 GB at 8K and 17.3 GB at 32K.
Where can I download JiRackDeltaNet 70b GGUF?
The files are on Hugging Face in the CMSManhattan/JiRackDeltaNet_70b 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 70b 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.