LI

Ling 3.0 Flash Sante

LingGGUF by bartowskiUpdated 2026-10-25
Download on Hugging Face
Parameters127B
Context256K
Layers43
Architecturebailingmoe3
Smallest quant1.0 GB
Quick answer

Ling 3.0 Flash Sante needs about 96.8 GB of memory at Q4_K_M (a 80.4 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 27 quants, from 1.0 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 Sante – a 127B parameter healthcare‑focused LLM

Ling 3.0 Flash Sante is a 127B parameter model built on the Ling family with a hybrid‑linear MoE architecture. It supports long contexts up to 262144 tokens and is optimized for medical reasoning, tool use, and research workflows.

Good at

  • Medical reasoning
  • Tool‑assisted workflows
  • Long‑document analysis

Limits

  • No vision support
  • Requires significant VRAM for higher‑quality quants
  • License is MIT

Best for

  • Clinical research summaries
  • Healthcare data analysis
  • Multi‑step medical queries

Who it’s for. Researchers, clinicians, and developers needing a large language model with strong medical knowledge and tool‑calling capabilities. The model is a research tool and not a medical device.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—1.0 GB 17.3 GB
Too big Get file →
IQ1_S29.8 GB 46.2 GB
Too big Get file →
IQ1_M33.0 GB 49.4 GB
Too big Get file →
IQ2_XXS38.4 GB 54.8 GB
Too big Get file →
IQ2_XS40.3 GB 56.7 GB
Too big Get file →
IQ2_S42.7 GB 59.1 GB
Too big Get file →
IQ2_M47.1 GB 63.4 GB
Too big Get file →
Q2_K49.5 GB 65.9 GB
Too big Get file →
IQ3_XXS55.7 GB (2 parts) 72.0 GB
Too big Get file →
IQ3_XS58.6 GB (2 parts) 74.9 GB
Too big Get file →
Q3_K_S58.6 GB (2 parts) 74.9 GB
Too big Get file →
Q3_K_M61.5 GB (2 parts) 77.9 GB
Too big Get file →
Q3_K_L65.1 GB (2 parts) 81.4 GB
Too big Get file →
IQ3_M69.3 GB (2 parts) 85.7 GB
Too big Get file →
IQ4_XS71.1 GB (2 parts) 87.5 GB
Too big Get file →
Q4_072.8 GB (2 parts) 89.2 GB
Too big Get file →
Q4_K_S75.7 GB (2 parts) 92.1 GB
Too big Get file →
Q4_180.2 GB (3 parts) 96.6 GB
Too big Get file →
Q4_K_M80.4 GB (3 parts) 96.8 GB
Too big Get file →
IQ4_NL80.4 GB (3 parts) 96.8 GB
Too big Get file →
Q4_K_L86.6 GB (3 parts) 103.0 GB
Too big Get file →
Q5_K_S90.7 GB (3 parts) 107.1 GB
Too big Get file →
Q5_K_M97.6 GB (3 parts) 114.0 GB
Too big Get file →
Q6_K_S106.3 GB (3 parts) 122.7 GB
Too big Get file →
Q6_K111.4 GB (3 parts) 127.8 GB
Too big Get file →
Q8_0135.6 GB (4 parts) 152.0 GB
Too big Get file →
BF16255.1 GB (7 parts) 271.5 GB
Too big Get file →

For 8 GB VRAM, use IQ1_S (29.8 GB file, 46.2 GB memory at 8 k context). For 16 GB VRAM, Q4_K_M (80.39 GB file, 96.8 GB memory) is a good balance. Larger VRAM allows Q8_0 or BF16 for higher fidelity.

What GPU do you need for Ling 3.0 Flash Sante?

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 (1.0 GB file, about 17.3 GB in use).
  • 32 GB VRAM: the best quant that fits is the main file (1.0 GB file, about 17.3 GB in use).
  • 48 GB VRAM: the best quant that fits is IQ1_S (29.8 GB file, about 46.2 GB in use).

Which Ling 3.0 Flash Sante quant should you choose?

Q4_K_M is the usual starting point for Ling 3.0 Flash Sante: it balances file size and quality well. Here it is a 80.4 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 1.0 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

Architecturebailingmoe3
Parameters127B (approximate, mixture of experts)
Layers43
Trained context262,144 tokens
KV cache (fp16)1892 KB per token

Source

Quantized bybartowski
FamilyLing
Licensemit
Downloads (HF)3,165
Last updated2026-10-25

Frequently asked questions about Ling 3.0 Flash Sante

How much VRAM does Ling 3.0 Flash Sante need?

About 96.8 GB at Q4_K_M with an 8K context window. That is the 80.4 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 3.0 Flash Sante on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 17.3 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Ling 3.0 Flash Sante GGUF?

It depends on the quant: file is 1.0 GB, IQ1_S is 29.8 GB, IQ1_M is 33.0 GB, IQ2_XXS is 38.4 GB, IQ2_XS is 40.3 GB, IQ2_S is 42.7 GB and 21 more.

What context length does Ling 3.0 Flash Sante 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 Sante GGUF?

The files are on Hugging Face in the bartowski/Ling-3.0-flash-Sante-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 Sante 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 Sante on 8 GB VRAM?

Use the IQ1_S quantization; it requires about 46.2 GB memory at 8 k context, which is beyond 8 GB VRAM, so it is not feasible.

Does the model support vision tasks?

No, the model only supports text input.

What is the license of this model?

The model is released under the MIT license.

Other GGUFs of Ling-3.0-flash-Sante

Similar models

Browse all →

More from bartowski

All by bartowski →

More Ling models

All Ling →

Other large models

All large models →