ling3 tiny coder ckpts needs about 9.8 GB of memory at Q4_K_M (a 4.8 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 6 quants, from 4.8 GB (Q4_K_M) to 15.8 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 17.7 GB.
ling3 tiny coder ckpts is a 7.89B-parameter Ling model in GGUF format, quantized by maternion. Its trained context length is 128K tokens. The repository has 6 quant files, from 4.8 GB (Q4_K_M) to 15.8 GB (BF16).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 4.8 GB | 9.8 GB | Too big | Get file → | |
| Q4_K_M | 4.8 GB | 9.8 GB | Too big | Get file → | |
| Q8_0 | 8.4 GB | 13.3 GB | Too big | Get file → | |
| Q8_0 | 8.4 GB | 13.3 GB | Too big | Get file → | |
| BF16 | 15.8 GB | 20.7 GB | Too big | Get file → | |
| BF16 | 15.8 GB | 20.7 GB | Too big | Get file → |
What GPU do you need for ling3 tiny coder ckpts?
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: the best quant that fits is Q4_K_M (4.8 GB file, about 9.8 GB in use).
- 16 GB VRAM: the best quant that fits is Q8_0 (8.4 GB file, about 13.3 GB in use).
- 24 GB VRAM: the best quant that fits is BF16 (15.8 GB file, about 20.7 GB in use).
Which ling3 tiny coder ckpts quant should you choose?
Q4_K_M is the usual starting point for ling3 tiny coder ckpts: it balances file size and quality well. Here it is a 4.8 GB file.
The Q8_0 file is 8.4 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.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about ling3 tiny coder ckpts
How much VRAM does ling3 tiny coder ckpts need?
About 9.8 GB at Q4_K_M with an 8K context window. That is the 4.8 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 ling3 tiny coder ckpts on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 9.8 GB, so you would need a larger GPU or CPU offloading.
What is the file size of ling3 tiny coder ckpts GGUF?
It depends on the quant: Q4_K_M is 4.8 GB, Q4_K_M is 4.8 GB, Q8_0 is 8.4 GB, Q8_0 is 8.4 GB, BF16 is 15.8 GB, BF16 is 15.8 GB.
What context length does ling3 tiny coder ckpts support?
The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 4.4 GB at 8K and 17.7 GB at 32K.
Where can I download ling3 tiny coder ckpts GGUF?
The files are on Hugging Face in the maternion/ling3-tiny-coder-ckpts repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does ling3 tiny coder ckpts 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.