KwaiCoder AutoThink Preview needs about 27.8 GB of memory at Q4_K_M (a 24.6 GB file) with an 8K context window, so it fits on a 32 GB GPU. This repository has 4 quants, from 21.3 GB (Q3_K_L) to 43.1 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 10.7 GB.
KwaiCoder AutoThink Preview is a 40.6B-parameter Kwaicoder model in GGUF format, quantized by lmstudio-community. Its trained context length is 32K tokens. The repository has 4 quant files, from 21.3 GB (Q3_K_L) to 43.1 GB (Q8_0).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q3_K_L | 21.3 GB | 24.5 GB | Too big | Get file → | |
| Q4_K_M | 24.6 GB | 27.8 GB | Too big | Get file → | |
| Q6_K | 33.3 GB | 36.5 GB | Too big | Get file → | |
| Q8_0 | 43.1 GB | 46.3 GB | Too big | Get file → |
What GPU do you need for KwaiCoder AutoThink Preview?
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: the best quant that fits is Q4_K_M (24.6 GB file, about 27.8 GB in use).
- 48 GB VRAM: the best quant that fits is Q8_0 (43.1 GB file, about 46.3 GB in use).
Which KwaiCoder AutoThink Preview quant should you choose?
Q4_K_M is the usual starting point for KwaiCoder AutoThink Preview: it balances file size and quality well. Here it is a 24.6 GB file.
The Q8_0 file is 43.1 GB, about 1.8 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.
If memory is tight, the smallest file is Q3_K_L at 21.3 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 KwaiCoder AutoThink Preview
How much VRAM does KwaiCoder AutoThink Preview need?
About 27.8 GB at Q4_K_M with an 8K context window. That is the 24.6 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 KwaiCoder AutoThink Preview on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 24.5 GB, so you would need a larger GPU or CPU offloading.
What is the file size of KwaiCoder AutoThink Preview GGUF?
It depends on the quant: Q3_K_L is 21.3 GB, Q4_K_M is 24.6 GB, Q6_K is 33.3 GB, Q8_0 is 43.1 GB.
What context length does KwaiCoder AutoThink Preview support?
The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 2.7 GB at 8K and 10.7 GB at 32K.
Where can I download KwaiCoder AutoThink Preview GGUF?
The files are on Hugging Face in the lmstudio-community/KwaiCoder-AutoThink-preview-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 KwaiCoder AutoThink Preview 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.