inkling needs about 485.2 GB of memory at Q3_K_XL (a 432.8 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 7 quants, from 270.2 GB (IQ1_S) to 1894.3 GB (BF16).
inkling is a 947B-parameter Inkling model in GGUF format, quantized by zurichquant. Its trained context length is 1024K tokens. The repository has 7 quant files, from 270.2 GB (IQ1_S) to 1894.3 GB (BF16).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ1_S | 270.2 GB (7 parts) | 303.1 GB | Too big | Get file → | |
| IQ1_M | 285.0 GB (7 parts) | 319.7 GB | Too big | Get file → | |
| Q2_K_XL | 317.3 GB (8 parts) | 355.9 GB | Too big | Get file → | |
| Q3_K_XL | 432.8 GB (10 parts) | 485.2 GB | Too big | Get file → | |
| Q4_K_XL | 587.0 GB (14 parts) | 658.0 GB | Too big | Get file → | |
| Q8_0 | 856.8 GB (19 parts) | 960.1 GB | Too big | Get file → | |
| BF16 | 1894.3 GB (41 parts) | 2122.1 GB | Too big | Get file → |
What GPU do you need for inkling?
These figures add the file size, an fp16 KV cache at an 8K context window 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: no quant fits at an 8K context.
Which inkling quant should you choose?
Q3_K_XL (432.8 GB) is the middle option in this repository. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.
If memory is tight, the smallest file is IQ1_S at 270.2 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 inkling
How much VRAM does inkling need?
About 485.2 GB at Q3_K_XL with an 8K context window. That is the 432.8 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 inkling on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 303.1 GB, so you would need a larger GPU or CPU offloading.
What is the file size of inkling GGUF?
It depends on the quant: IQ1_S is 270.2 GB, IQ1_M is 285.0 GB, Q2_K_XL is 317.3 GB, Q3_K_XL is 432.8 GB, Q4_K_XL is 587.0 GB, Q8_0 is 856.8 GB and 1 more.
What context length does inkling support?
The GGUF header lists a trained context length of 1,048,576 tokens (1024K).
Where can I download inkling GGUF?
The files are on Hugging Face in the zurichquant/inkling-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 inkling 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.