Ling-3.1-flash needs about 427.8 GB of memory at Q4_K_M (a 374.1 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 5 quants, from 10.1 GB (Q8_0) to 439.7 GB (Q5_K_M). Longer context needs more: at 32K tokens the KV cache alone adds about 212.6 GB.
Ling-3.1-flash is a 564B-parameter Ling model in GGUF format, quantized by vultr. Its trained context length is 256K tokens. The repository has 5 quant files, from 10.1 GB (Q8_0) to 439.7 GB (Q5_K_M).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q8_0 | 10.1 GB | 63.7 GB | Too big | Get file → | |
| IQ3_S | 267.4 GB (2 parts) | 321.0 GB | Too big | Get file → | |
| IQ3_M | 270.0 GB (2 parts) | 323.7 GB | Too big | Get file → | |
| Q4_K_M | 374.1 GB (3 parts) | 427.8 GB | Too big | Get file → | |
| Q5_K_M | 439.7 GB (3 parts) | 493.3 GB | Too big | Get file → |
What GPU do you need for Ling-3.1-flash?
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: no quant fits at an 8K context.
Which Ling-3.1-flash quant should you choose?
Q4_K_M is the usual starting point for Ling-3.1-flash: it balances file size and quality well. Here it is a 374.1 GB file.
The Q8_0 file is 10.1 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 10.1 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-3.1-flash
How much VRAM does Ling-3.1-flash need?
About 427.8 GB at Q4_K_M with an 8K context window. That is the 374.1 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 Ling-3.1-flash on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 63.7 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Ling-3.1-flash GGUF?
It depends on the quant: Q8_0 is 10.1 GB, IQ3_S is 267.4 GB, IQ3_M is 270.0 GB, Q4_K_M is 374.1 GB, Q5_K_M is 439.7 GB.
What context length does Ling-3.1-flash support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 53.2 GB at 8K and 212.6 GB at 32K.
Where can I download Ling-3.1-flash GGUF?
The files are on Hugging Face in the vultr/Ling-3.1-flash-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-3.1-flash 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.