ornith mtp fiddling needs about 19.0 GB of memory at its main file (a 16.5 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 9 quants, from 0.5 GB (Q4_0) to 25.3 GB.
ornith mtp fiddling is a 34.7B-parameter Ornith model in GGUF format, quantized by burningfeet. Its trained context length is 256K tokens. The repository has 9 quant files, from 0.5 GB (Q4_0) to 25.3 GB.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_0 | 0.5 GB | 1.0 GB | Fits | Get file → | |
| BF16 | 1.7 GB | 2.4 GB | Fits | Get file → | |
| — | 13.5 GB | 15.6 GB | Too big | Get file → | |
| — | 16.5 GB | 19.0 GB | Too big | Get file → | |
| — | 16.5 GB | 19.0 GB | Too big | Get file → | |
| — | 22.8 GB | 26.1 GB | Too big | Get file → | |
| — | 22.8 GB | 26.1 GB | Too big | Get file → | |
| — | 25.3 GB | 28.8 GB | Too big | Get file → | |
| — | 25.3 GB | 28.8 GB | Too big | Get file → |
What GPU do you need for ornith mtp fiddling?
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: the best quant that fits is BF16 (1.7 GB file, about 2.4 GB in use).
- 6 GB VRAM: the best quant that fits is BF16 (1.7 GB file, about 2.4 GB in use).
- 8 GB VRAM: the best quant that fits is BF16 (1.7 GB file, about 2.4 GB in use).
- 12 GB VRAM: the best quant that fits is BF16 (1.7 GB file, about 2.4 GB in use).
- 16 GB VRAM: the best quant that fits is the main file (13.5 GB file, about 15.6 GB in use).
- 24 GB VRAM: the best quant that fits is the main file (16.5 GB file, about 19.0 GB in use).
- 32 GB VRAM: the best quant that fits is the main file (25.3 GB file, about 28.8 GB in use).
Which ornith mtp fiddling quant should you choose?
If memory is tight, the smallest file is Q4_0 at 0.5 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 ornith mtp fiddling
How much VRAM does ornith mtp fiddling need?
About 19.0 GB at its main file with an 8K context window. That is the 16.5 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 ornith mtp fiddling on an 8 GB GPU?
Yes, with BF16: the 1.7 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 ornith mtp fiddling GGUF?
It depends on the quant: Q4_0 is 0.5 GB, BF16 is 1.7 GB, file is 13.5 GB, file is 16.5 GB, file is 16.5 GB, file is 22.8 GB and 3 more.
What context length does ornith mtp fiddling support?
The GGUF header lists a trained context length of 262,144 tokens (256K).
Where can I download ornith mtp fiddling GGUF?
The files are on Hugging Face in the burningfeet/ornith-mtp-fiddling repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.