QuadConnect2.5-1.5B-v0.1.0b needs about 1.7 GB of memory at Q4_0 (a 0.9 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 2 quants, from 0.9 GB (Q4_0) to 1.6 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 0.9 GB.
QuadConnect2.5-1.5B-v0.1.0b is a 1.54B-parameter Quadconnect model in GGUF format, quantized by Lyte. Its trained context length is 32K tokens. The repository has 2 quant files, from 0.9 GB (Q4_0) to 1.6 GB (Q8_0).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_0 | 0.9 GB | 1.7 GB | Fits | Get file → | |
| Q8_0 | 1.6 GB | 2.4 GB | Fits | Get file → |
What GPU do you need for QuadConnect2.5-1.5B-v0.1.0b?
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 Q8_0 (1.6 GB file, about 2.4 GB in use).
Which QuadConnect2.5-1.5B-v0.1.0b quant should you choose?
Q4_0 (0.9 GB) is the middle option in this repository. 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 QuadConnect2.5-1.5B-v0.1.0b
How much VRAM does QuadConnect2.5-1.5B-v0.1.0b need?
About 1.7 GB at Q4_0 with an 8K context window. That is the 0.9 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 QuadConnect2.5-1.5B-v0.1.0b on an 8 GB GPU?
Yes, with Q8_0: the 1.6 GB file needs about 2.4 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of QuadConnect2.5-1.5B-v0.1.0b GGUF?
It depends on the quant: Q4_0 is 0.9 GB, Q8_0 is 1.6 GB.
What context length does QuadConnect2.5-1.5B-v0.1.0b support?
The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 0.2 GB at 8K and 0.9 GB at 32K.
Where can I download QuadConnect2.5-1.5B-v0.1.0b GGUF?
The files are on Hugging Face in the Lyte/QuadConnect2.5-1.5B-v0.1.0b repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.