Instella MoE 16B A3B Think needs about 12.2 GB of memory at Q4_K_M (a 10.5 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 5 quants, from 9.6 GB (Q4_K_S) to 31.7 GB (F16).
Instella MoE 16B A3B Think is a 15.9B-parameter Instella model in GGUF format, quantized by TULLUS. Its trained context length is 32K tokens. The repository has 5 quant files, from 9.6 GB (Q4_K_S) to 31.7 GB (F16).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_S | 9.6 GB | 11.3 GB | Too big | Get file → | |
| Q4_K_M | 10.5 GB | 12.2 GB | Too big | Get file → | |
| Q5_K_M | 12.0 GB | 13.9 GB | Too big | Get file → | |
| Q6_K | 14.2 GB | 16.4 GB | Too big | Get file → | |
| F16 | 31.7 GB | 36.0 GB | Too big | Get file → |
What GPU do you need for Instella MoE 16B A3B Think?
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: the best quant that fits is Q4_K_S (9.6 GB file, about 11.3 GB in use).
- 16 GB VRAM: the best quant that fits is Q5_K_M (12.0 GB file, about 13.9 GB in use).
- 24 GB VRAM: the best quant that fits is Q6_K (14.2 GB file, about 16.4 GB in use).
- 32 GB VRAM: the best quant that fits is Q6_K (14.2 GB file, about 16.4 GB in use).
- 48 GB VRAM: the best quant that fits is F16 (31.7 GB file, about 36.0 GB in use).
Which Instella MoE 16B A3B Think quant should you choose?
Q4_K_M is the usual starting point for Instella MoE 16B A3B Think: it balances file size and quality well. Here it is a 10.5 GB file.
If memory is tight, the smallest file is Q4_K_S at 9.6 GB, with the quality trade-offs that come with fewer bits. The usual sweet spot between file size and quality, and the quant most people start with.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Instella MoE 16B A3B Think
How much VRAM does Instella MoE 16B A3B Think need?
About 12.2 GB at Q4_K_M with an 8K context window. That is the 10.5 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 Instella MoE 16B A3B Think on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 11.3 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Instella MoE 16B A3B Think GGUF?
It depends on the quant: Q4_K_S is 9.6 GB, Q4_K_M is 10.5 GB, Q5_K_M is 12.0 GB, Q6_K is 14.2 GB, F16 is 31.7 GB.
What context length does Instella MoE 16B A3B Think support?
The GGUF header lists a trained context length of 32,768 tokens (32K).
Where can I download Instella MoE 16B A3B Think GGUF?
The files are on Hugging Face in the TULLUS/Instella-MoE-16B-A3B-Think-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 Instella MoE 16B A3B Think 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.