thinkingmachines.Inkling needs about 590.7 GB of memory at Q4_K_M (a 572.5 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 4 quants, from 246.5 GB (IQ2_XXS) to 572.5 GB (Q4_K_M). Longer context needs more: at 32K tokens the KV cache alone adds about 70.9 GB.
thinkingmachines.Inkling is a 947B-parameter Inkling model in GGUF format, quantized by DevQuasar. Its trained context length is 1024K tokens. The repository has 4 quant files, from 246.5 GB (IQ2_XXS) to 572.5 GB (Q4_K_M).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ2_XXS | 246.5 GB (17 parts) | 264.7 GB | Too big | Get file → | |
| Q2_K | 344.0 GB (24 parts) | 362.2 GB | Too big | Get file → | |
| Q3_K_M | 451.0 GB (33 parts) | 469.3 GB | Too big | Get file → | |
| Q4_K_M | 572.5 GB (40 parts) | 590.7 GB | Too big | Get file → |
What GPU do you need for thinkingmachines.Inkling?
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: no quant fits at an 8K context.
Which thinkingmachines.Inkling quant should you choose?
Q4_K_M is the usual starting point for thinkingmachines.Inkling: it balances file size and quality well. Here it is a 572.5 GB file.
If memory is tight, the smallest file is IQ2_XXS at 246.5 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 thinkingmachines.Inkling
How much VRAM does thinkingmachines.Inkling need?
About 590.7 GB at Q4_K_M with an 8K context window. That is the 572.5 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 thinkingmachines.Inkling on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 264.7 GB, so you would need a larger GPU or CPU offloading.
What is the file size of thinkingmachines.Inkling GGUF?
It depends on the quant: IQ2_XXS is 246.5 GB, Q2_K is 344.0 GB, Q3_K_M is 451.0 GB, Q4_K_M is 572.5 GB.
What context length does thinkingmachines.Inkling support?
The GGUF header lists a trained context length of 1,048,576 tokens (1024K). The KV cache grows with the context you use: about 17.7 GB at 8K and 70.9 GB at 32K.
Where can I download thinkingmachines.Inkling GGUF?
The files are on Hugging Face in the DevQuasar/thinkingmachines.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 thinkingmachines.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.