Qwable v1 needs about 34.3 GB of memory at Q6_0 (a 33.1 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 5 quants, from 20.2 GB (Q4_0) to 37.3 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 2.8 GB.
Qwable v1 is a 35.5B-parameter Lordx model in GGUF format, quantized by rcmorano. Its trained context length is 256K tokens. The repository has 5 quant files, from 20.2 GB (Q4_0) to 37.3 GB (Q8_0).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_0 | 20.2 GB | 21.4 GB | Too big | Get file → | |
| Q6_0 | 29.4 GB | 30.6 GB | Too big | Get file → | |
| Q6_0 | 33.1 GB | 34.3 GB | Too big | Get file → | |
| Q8_0 | 36.7 GB | 37.9 GB | Too big | Get file → | |
| Q8_0 | 37.3 GB | 38.5 GB | Too big | Get file → |
What GPU do you need for Qwable v1?
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: the best quant that fits is Q4_0 (20.2 GB file, about 21.4 GB in use).
- 32 GB VRAM: the best quant that fits is Q6_0 (29.4 GB file, about 30.6 GB in use).
- 48 GB VRAM: the best quant that fits is Q8_0 (37.3 GB file, about 38.5 GB in use).
Which Qwable v1 quant should you choose?
Q6_0 (33.1 GB) is the middle option in this repository. Very close to the original quality for most uses, at a clearly larger size than 4-bit.
If memory is tight, the smallest file is Q4_0 at 20.2 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 Qwable v1
How much VRAM does Qwable v1 need?
About 34.3 GB at Q6_0 with an 8K context window. That is the 33.1 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 Qwable v1 on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 21.4 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Qwable v1 GGUF?
It depends on the quant: Q4_0 is 20.2 GB, Q6_0 is 29.4 GB, Q6_0 is 33.1 GB, Q8_0 is 36.7 GB, Q8_0 is 37.3 GB.
What context length does Qwable v1 support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 0.7 GB at 8K and 2.8 GB at 32K.
Where can I download Qwable v1 GGUF?
The files are on Hugging Face in the rcmorano/bartowski-lordx64_Qwable-v1-35B-A3B-ROCMFPX repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does Qwable v1 use?
Hugging Face lists the license as agpl-3.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.