Sakura TwIL LM3 Pro needs about 3.4 GB of memory at Q4_K_M (a 2.2 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 3 quants, from 2.2 GB (Q4_K_M) to 3.0 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 2.7 GB.
Sakura TwIL LM3 Pro is a 3.66B-parameter Twil model in GGUF format, quantized by webmp3. Its trained context length is 128K tokens. The repository has 3 quant files, from 2.2 GB (Q4_K_M) to 3.0 GB (Q6_K).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 2.2 GB | 3.4 GB | Fits | Get file → | |
| Q5_K_M | 2.6 GB | 3.7 GB | Fits | Get file → | |
| Q6_K | 3.0 GB | 4.1 GB | Fits | Get file → |
What GPU do you need for Sakura TwIL LM3 Pro?
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: the best quant that fits is Q5_K_M (2.6 GB file, about 3.7 GB in use).
- 6 GB VRAM: the best quant that fits is Q6_K (3.0 GB file, about 4.1 GB in use).
Which Sakura TwIL LM3 Pro quant should you choose?
Q4_K_M is the usual starting point for Sakura TwIL LM3 Pro: it balances file size and quality well. Here it is a 2.2 GB file.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Sakura TwIL LM3 Pro
How much VRAM does Sakura TwIL LM3 Pro need?
About 3.4 GB at Q4_K_M with an 8K context window. That is the 2.2 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 Sakura TwIL LM3 Pro on an 8 GB GPU?
Yes, with Q6_K: the 3.0 GB file needs about 4.1 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Sakura TwIL LM3 Pro GGUF?
It depends on the quant: Q4_K_M is 2.2 GB, Q5_K_M is 2.6 GB, Q6_K is 3.0 GB.
What context length does Sakura TwIL LM3 Pro support?
The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 0.7 GB at 8K and 2.7 GB at 32K.
Where can I download Sakura TwIL LM3 Pro GGUF?
The files are on Hugging Face in the webmp3/Sakura-TwIL-LM3-Pro-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 Sakura TwIL LM3 Pro 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.