Ling 3.0 Flash needs about 94.2 GB of memory at Q4_K_M (a 77.8 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 29 quants, from 0.5 GB to 255.1 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 63.5 GB.
Ling 3.0 Flash – 130 B parameters, 262 K context, MIT license
Ling 3.0 Flash is a 130 B parameter model with a 262,144‑token context window. It uses a native hybrid‑linear architecture and 1/64 sparse MoE. The model is released under the MIT license and supports text input only.
Good at
- Long‑context reasoning
- Hybrid linear attention
- Sparse MoE efficiency
Limits
- Large VRAM requirement for full precision
- No vision or audio support
- Requires llama.cpp b10472 or newer
Best for
- Production agent workflows
- Long‑horizon coding tasks
- Research‑grade reasoning
Who it’s for. Developers and researchers who need a large‑parameter model with extended context for agentic or coding applications. The model is suitable for environments that can allocate the necessary GPU memory and run llama.cpp.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.5 GB | 16.9 GB | Too big | Get file → | |
| IQ1_S | 27.6 GB | 43.9 GB | Too big | Get file → | |
| IQ1_M | 30.6 GB | 46.9 GB | Too big | Get file → | |
| IQ2_XXS | 35.2 GB | 51.6 GB | Too big | Get file → | |
| IQ2_XS | 39.0 GB | 55.4 GB | Too big | Get file → | |
| IQ2_S | 39.7 GB | 56.1 GB | Too big | Get file → | |
| IQ2_M | 43.6 GB | 60.0 GB | Too big | Get file → | |
| Q2_K | 45.9 GB | 62.3 GB | Too big | Get file → | |
| Q2_K_L | 46.3 GB | 62.7 GB | Too big | Get file → | |
| IQ3_XXS | 54.1 GB (2 parts) | 70.5 GB | Too big | Get file → | |
| Q3_K_S | 56.3 GB (2 parts) | 72.7 GB | Too big | Get file → | |
| IQ3_XS | 58.9 GB (2 parts) | 75.3 GB | Too big | Get file → | |
| Q3_K_M | 59.0 GB (2 parts) | 75.3 GB | Too big | Get file → | |
| Q3_K_L | 61.4 GB (2 parts) | 77.8 GB | Too big | Get file → | |
| IQ3_M | 61.5 GB (2 parts) | 77.9 GB | Too big | Get file → | |
| Q3_K_XL | 61.8 GB (2 parts) | 78.2 GB | Too big | Get file → | |
| IQ4_XS | 68.7 GB (2 parts) | 85.1 GB | Too big | Get file → | |
| IQ4_NL | 72.6 GB (2 parts) | 88.9 GB | Too big | Get file → | |
| Q4_0 | 72.8 GB (2 parts) | 89.2 GB | Too big | Get file → | |
| Q4_K_S | 75.0 GB (2 parts) | 91.4 GB | Too big | Get file → | |
| Q4_K_M | 77.8 GB (2 parts) | 94.2 GB | Too big | Get file → | |
| Q4_K_L | 78.1 GB (2 parts) | 94.5 GB | Too big | Get file → | |
| Q4_1 | 80.2 GB (3 parts) | 96.6 GB | Too big | Get file → | |
| Q5_K_S | 87.9 GB (3 parts) | 104.3 GB | Too big | Get file → | |
| Q5_K_M | 90.7 GB (3 parts) | 107.0 GB | Too big | Get file → | |
| Q5_K_L | 90.9 GB (3 parts) | 107.3 GB | Too big | Get file → | |
| Q6_K | 109.3 GB (3 parts) | 125.6 GB | Too big | Get file → | |
| Q8_0 | 135.6 GB (4 parts) | 152.0 GB | Too big | Get file → | |
| BF16 | 255.1 GB (7 parts) | 271.5 GB | Too big | Get file → |
For 8 GB VRAM, use Q4_K_M (77.8 GB file, ~94 GB memory at 8 k context). For 16 GB VRAM, Q4_K_L (78.1 GB file, ~94.5 GB memory). For 32 GB VRAM, Q5_K_M (90.66 GB file, ~107 GB memory). Estimates are approximate.
What GPU do you need for Ling 3.0 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: the best quant that fits is the main file (0.5 GB file, about 16.9 GB in use).
- 32 GB VRAM: the best quant that fits is the main file (0.5 GB file, about 16.9 GB in use).
- 48 GB VRAM: the best quant that fits is IQ1_M (30.6 GB file, about 46.9 GB in use).
Which Ling 3.0 Flash quant should you choose?
Q4_K_M is the usual starting point for Ling 3.0 Flash: it balances file size and quality well. Here it is a 77.8 GB file.
The Q8_0 file is 135.6 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 the first one in the table at 0.5 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 3.0 Flash
How much VRAM does Ling 3.0 Flash need?
About 94.2 GB at Q4_K_M with an 8K context window. That is the 77.8 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 on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 16.9 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Ling 3.0 Flash GGUF?
It depends on the quant: file is 0.5 GB, IQ1_S is 27.6 GB, IQ1_M is 30.6 GB, IQ2_XXS is 35.2 GB, IQ2_XS is 39.0 GB, IQ2_S is 39.7 GB and 23 more.
What context length does Ling 3.0 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 15.9 GB at 8K and 63.5 GB at 32K.
Where can I download Ling 3.0 Flash GGUF?
The files are on Hugging Face in the bartowski/Ling-3.0-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 3.0 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.
Can I run Ling 3.0 Flash on 8 GB VRAM?
No, the smallest quant requires at least 16 GB VRAM. The Q4_K_M quant needs about 94 GB memory at 8 k context.
Does Ling 3.0 Flash support image input?
No, the model only supports text input.