Ling flash base 2.0 i1 needs about 49.3 GB of memory at IQ3_XS (a 43.6 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 7 quants, from 0.3 GB to 46.6 GB (IQ3_M).
Ling flash base 2.0 i1 is a 106B-parameter Ling model in GGUF format, quantized by mradermacher. Its trained context length is 32K tokens. The repository has 7 quant files, from 0.3 GB to 46.6 GB (IQ3_M).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.3 GB | 0.8 GB | Fits | Get file → | |
| Q2_K | 38.9 GB | 44.0 GB | Too big | Get file → | |
| IQ3_XXS | 41.0 GB | 46.5 GB | Too big | Get file → | |
| IQ3_XS | 43.6 GB | 49.3 GB | Too big | Get file → | |
| IQ3_S | 46.0 GB | 52.0 GB | Too big | Get file → | |
| Q3_K_S | 46.0 GB | 52.0 GB | Too big | Get file → | |
| IQ3_M | 46.6 GB | 52.7 GB | Too big | Get file → |
What GPU do you need for Ling flash base 2.0 i1?
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 the main file (0.3 GB file, about 0.8 GB in use).
- 6 GB VRAM: the best quant that fits is the main file (0.3 GB file, about 0.8 GB in use).
- 8 GB VRAM: the best quant that fits is the main file (0.3 GB file, about 0.8 GB in use).
- 12 GB VRAM: the best quant that fits is the main file (0.3 GB file, about 0.8 GB in use).
- 16 GB VRAM: the best quant that fits is the main file (0.3 GB file, about 0.8 GB in use).
- 24 GB VRAM: the best quant that fits is the main file (0.3 GB file, about 0.8 GB in use).
- 32 GB VRAM: the best quant that fits is the main file (0.3 GB file, about 0.8 GB in use).
- 48 GB VRAM: the best quant that fits is IQ3_XXS (41.0 GB file, about 46.5 GB in use).
Which Ling flash base 2.0 i1 quant should you choose?
IQ3_XS (43.6 GB) is the middle option in this repository. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.
If memory is tight, the smallest file is the first one in the table at 0.3 GB, with the quality trade-offs that come with fewer bits.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Ling flash base 2.0 i1
How much VRAM does Ling flash base 2.0 i1 need?
About 49.3 GB at IQ3_XS with an 8K context window. That is the 43.6 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 Ling flash base 2.0 i1 on an 8 GB GPU?
Yes, with the smaller files: the 0.3 GB file needs about 0.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Ling flash base 2.0 i1 GGUF?
It depends on the quant: file is 0.3 GB, Q2_K is 38.9 GB, IQ3_XXS is 41.0 GB, IQ3_XS is 43.6 GB, IQ3_S is 46.0 GB, Q3_K_S is 46.0 GB and 1 more.
What context length does Ling flash base 2.0 i1 support?
The GGUF header lists a trained context length of 32,768 tokens (32K).
Where can I download Ling flash base 2.0 i1 GGUF?
The files are on Hugging Face in the mradermacher/Ling-flash-base-2.0-i1-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 Ling flash base 2.0 i1 use?
Hugging Face lists the license as mit. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.