Ling-3.0-flash-Fin needs about 98.8 GB of memory at Q4_K_M (a 82.8 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 5 quants, from 4.1 GB (Q8_0) to 97.2 GB (Q5_K_M). Longer context needs more: at 32K tokens the KV cache alone adds about 62.0 GB.
Ling-3.0-flash-Fin is a 124B-parameter Ling model in GGUF format, quantized by vultr. Its trained context length is 256K tokens. The repository has 5 quant files, from 4.1 GB (Q8_0) to 97.2 GB (Q5_K_M).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q8_0 | 4.1 GB | 20.1 GB | Too big | Get file → | |
| IQ3_S | 59.2 GB | 75.2 GB | Too big | Get file → | |
| IQ3_M | 59.7 GB | 75.7 GB | Too big | Get file → | |
| Q4_K_M | 82.8 GB | 98.8 GB | Too big | Get file → | |
| Q5_K_M | 97.2 GB | 113.2 GB | Too big | Get file → |
What GPU do you need for Ling-3.0-flash-Fin?
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 Q8_0 (4.1 GB file, about 20.1 GB in use).
- 32 GB VRAM: the best quant that fits is Q8_0 (4.1 GB file, about 20.1 GB in use).
- 48 GB VRAM: the best quant that fits is Q8_0 (4.1 GB file, about 20.1 GB in use).
Which Ling-3.0-flash-Fin quant should you choose?
Q4_K_M is the usual starting point for Ling-3.0-flash-Fin: it balances file size and quality well. Here it is a 82.8 GB file.
The Q8_0 file is 4.1 GB, about 0.0 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 Q8_0 at 4.1 GB, with the quality trade-offs that come with fewer bits. Close to lossless. It costs roughly twice the memory of a 4-bit file, so it suits cases where you have plenty of VRAM.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Ling-3.0-flash-Fin
How much VRAM does Ling-3.0-flash-Fin need?
About 98.8 GB at Q4_K_M with an 8K context window. That is the 82.8 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-3.0-flash-Fin on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 20.1 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Ling-3.0-flash-Fin GGUF?
It depends on the quant: Q8_0 is 4.1 GB, IQ3_S is 59.2 GB, IQ3_M is 59.7 GB, Q4_K_M is 82.8 GB, Q5_K_M is 97.2 GB.
What context length does Ling-3.0-flash-Fin support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 15.5 GB at 8K and 62.0 GB at 32K.
Where can I download Ling-3.0-flash-Fin GGUF?
The files are on Hugging Face in the vultr/Ling-3.0-flash-Fin-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-3.0-flash-Fin 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.