Ling 2.6 flash GGUF YMMV needs about 78.1 GB of memory at Q4_K_M (a 65.4 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 4 quants, from 32.0 GB (IQ2_XS) to 114.3 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 48.7 GB.
Ling 2.6 flash GGUF YMMV is a 108B-parameter Ling model in GGUF format, quantized by ssweens. Its trained context length is 128K tokens. The repository has 4 quant files, from 32.0 GB (IQ2_XS) to 114.3 GB (Q8_0).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ2_XS | 32.0 GB | 44.7 GB | Too big | Get file → | |
| Q2_K | 39.4 GB | 52.1 GB | Too big | Get file → | |
| Q4_K_M | 65.4 GB | 78.1 GB | Too big | Get file → | |
| Q8_0 | 114.3 GB | 127.0 GB | Too big | Get file → |
What GPU do you need for Ling 2.6 flash GGUF YMMV?
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: no quant fits at an 8K context.
- 32 GB VRAM: no quant fits at an 8K context.
- 48 GB VRAM: the best quant that fits is IQ2_XS (32.0 GB file, about 44.7 GB in use).
Which Ling 2.6 flash GGUF YMMV quant should you choose?
Q4_K_M is the usual starting point for Ling 2.6 flash GGUF YMMV: it balances file size and quality well. Here it is a 65.4 GB file.
The Q8_0 file is 114.3 GB, about 1.7 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.
If memory is tight, the smallest file is IQ2_XS at 32.0 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Ling 2.6 flash GGUF YMMV
How much VRAM does Ling 2.6 flash GGUF YMMV need?
About 78.1 GB at Q4_K_M with an 8K context window. That is the 65.4 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 2.6 flash GGUF YMMV on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 44.7 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Ling 2.6 flash GGUF YMMV GGUF?
It depends on the quant: IQ2_XS is 32.0 GB, Q2_K is 39.4 GB, Q4_K_M is 65.4 GB, Q8_0 is 114.3 GB.
What context length does Ling 2.6 flash GGUF YMMV support?
The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 12.2 GB at 8K and 48.7 GB at 32K.
Where can I download Ling 2.6 flash GGUF YMMV GGUF?
The files are on Hugging Face in the ssweens/Ling-2.6-flash-GGUF-YMMV 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 2.6 flash GGUF YMMV 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.