Mit ThinkDeeply 7B needs about 9.1 GB of memory at Q8_0 (a 8.1 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 5 quants, from 3.6 GB (TQ1_0) to 15.2 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 1.9 GB.
Mit ThinkDeeply 7B is a 7.62B-parameter Mit model in GGUF format, quantized by WinkingFace. Its trained context length is 32K tokens. The repository has 5 quant files, from 3.6 GB (TQ1_0) to 15.2 GB (F16).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| TQ1_0 | 3.6 GB | 4.5 GB | Fits | Get file → | |
| TQ2_0 | 3.9 GB | 4.8 GB | Fits | Get file → | |
| Q8_0 | 8.1 GB | 9.1 GB | Too big | Get file → | |
| BF16 | 15.2 GB | 16.2 GB | Too big | Get file → | |
| F16 | 15.2 GB | 16.2 GB | Too big | Get file → |
What GPU do you need for Mit ThinkDeeply 7B?
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: the best quant that fits is TQ2_0 (3.9 GB file, about 4.8 GB in use).
- 8 GB VRAM: the best quant that fits is TQ2_0 (3.9 GB file, about 4.8 GB in use).
- 12 GB VRAM: the best quant that fits is Q8_0 (8.1 GB file, about 9.1 GB in use).
- 16 GB VRAM: the best quant that fits is Q8_0 (8.1 GB file, about 9.1 GB in use).
- 24 GB VRAM: the best quant that fits is BF16 (15.2 GB file, about 16.2 GB in use).
Which Mit ThinkDeeply 7B quant should you choose?
Q8_0 (8.1 GB) is the middle option in this repository. Close to lossless. It costs roughly twice the memory of a 4-bit file, so it suits cases where you have plenty of VRAM.
If memory is tight, the smallest file is TQ1_0 at 3.6 GB, with the quality trade-offs that come with fewer bits. 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 Mit ThinkDeeply 7B
How much VRAM does Mit ThinkDeeply 7B need?
About 9.1 GB at Q8_0 with an 8K context window. That is the 8.1 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 Mit ThinkDeeply 7B on an 8 GB GPU?
Yes, with TQ2_0: the 3.9 GB file needs about 4.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Mit ThinkDeeply 7B GGUF?
It depends on the quant: TQ1_0 is 3.6 GB, TQ2_0 is 3.9 GB, Q8_0 is 8.1 GB, BF16 is 15.2 GB, F16 is 15.2 GB.
What context length does Mit ThinkDeeply 7B support?
The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 0.5 GB at 8K and 1.9 GB at 32K.
Where can I download Mit ThinkDeeply 7B GGUF?
The files are on Hugging Face in the WinkingFace/Mit-ThinkDeeply-7B-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 Mit ThinkDeeply 7B 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.