flex2 needs about 10.4 GB of memory at Q8_0 (a 8.7 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 2 quants, from 8.7 GB (Q8_0) to 10.0 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 4.8 GB.
flex2 is a 9.08B-parameter Flex model in GGUF format, quantized by mezattn. Its trained context length is 256K tokens. The repository has 2 quant files, from 8.7 GB (Q8_0) to 10.0 GB (Q8_0).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q8_0 | 8.7 GB | 10.4 GB | Too big | Get file → | |
| Q8_0 | 10.0 GB | 11.7 GB | Too big | Get file → |
What GPU do you need for flex2?
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: the best quant that fits is Q8_0 (10.0 GB file, about 11.7 GB in use).
Which flex2 quant should you choose?
Q8_0 (8.7 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.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Frequently asked questions about flex2
How much VRAM does flex2 need?
About 10.4 GB at Q8_0 with an 8K context window. That is the 8.7 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 flex2 on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 10.4 GB, so you would need a larger GPU or CPU offloading.
What is the file size of flex2 GGUF?
It depends on the quant: Q8_0 is 8.7 GB, Q8_0 is 10.0 GB.
What context length does flex2 support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 1.2 GB at 8K and 4.8 GB at 32K.
Where can I download flex2 GGUF?
The files are on Hugging Face in the mezattn/flex2 repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.