LI

Ling 3.0 Flash Fin

LingGGUF by bartowskiUpdated 2026-09-04
Download on Hugging Face
Parameters127B
Context256K
Layers43
Architecturebailingmoe3
Smallest quant0.5 GB
Quick answer

Ling 3.0 Flash Fin 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 Fin – finance‑focused LLM with 130B parameters

Ling 3.0 Flash Fin is a 130‑billion‑parameter model built on the bailingmoe3 architecture. It is trained on high‑quality financial data and supports a 262,144‑token context window. The model is released under the MIT license and is compatible with llama.cpp and vLLM runtimes.

Good at

  • Financial research and analysis
  • Source‑grounded retrieval
  • Spreadsheet and valuation tasks

Limits

  • No vision support
  • Requires large VRAM for higher quants
  • Tool usage only, no image input

Best for

  • Generating investment research reports
  • Automating spreadsheet calculations
  • Long‑horizon financial agent workflows

Who it’s for. Developers building finance‑centric applications that need source‑grounded answers and spreadsheet integration. The model is suitable for teams that can run it locally with sufficient GPU memory.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.5 GB 16.9 GB
Too big Get file →
IQ1_S27.6 GB 43.9 GB
Too big Get file →
IQ1_M30.6 GB 46.9 GB
Too big Get file →
IQ2_XXS35.2 GB 51.6 GB
Too big Get file →
IQ2_XS39.0 GB 55.4 GB
Too big Get file →
IQ2_S39.7 GB 56.1 GB
Too big Get file →
IQ2_M43.6 GB 60.0 GB
Too big Get file →
Q2_K45.9 GB 62.3 GB
Too big Get file →
Q2_K_L46.3 GB 62.7 GB
Too big Get file →
IQ3_XXS54.1 GB (2 parts) 70.5 GB
Too big Get file →
Q3_K_S56.3 GB (2 parts) 72.7 GB
Too big Get file →
IQ3_XS58.9 GB (2 parts) 75.3 GB
Too big Get file →
Q3_K_M59.0 GB (2 parts) 75.3 GB
Too big Get file →
Q3_K_L61.4 GB (2 parts) 77.8 GB
Too big Get file →
IQ3_M61.5 GB (2 parts) 77.9 GB
Too big Get file →
Q3_K_XL61.8 GB (2 parts) 78.2 GB
Too big Get file →
IQ4_XS68.7 GB (2 parts) 85.1 GB
Too big Get file →
IQ4_NL72.6 GB (2 parts) 88.9 GB
Too big Get file →
Q4_072.8 GB (2 parts) 89.2 GB
Too big Get file →
Q4_K_S75.0 GB (2 parts) 91.4 GB
Too big Get file →
Q4_K_M77.8 GB (2 parts) 94.2 GB
Too big Get file →
Q4_K_L78.1 GB (2 parts) 94.5 GB
Too big Get file →
Q4_180.2 GB (3 parts) 96.6 GB
Too big Get file →
Q5_K_S87.9 GB (3 parts) 104.3 GB
Too big Get file →
Q5_K_M90.7 GB (3 parts) 107.0 GB
Too big Get file →
Q5_K_L90.9 GB (3 parts) 107.3 GB
Too big Get file →
Q6_K109.3 GB (3 parts) 125.6 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 (27.57 GB, 43.9 GB RAM). For 16 GB VRAM, Q4_K_M (77.8 GB, 94.2 GB RAM) is a good balance. For 24 GB VRAM, Q5_K_M (90.66 GB, 107 GB RAM) offers higher quality. All estimates are approximate.

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 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 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 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

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)4,619
Last updated2026-09-04

Frequently asked questions about Ling 3.0 Flash Fin

How much VRAM does Ling 3.0 Flash Fin 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 Fin 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 Fin 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 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 15.9 GB at 8K and 63.5 GB at 32K.

Where can I download Ling 3.0 Flash Fin GGUF?

The files are on Hugging Face in the bartowski/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.

Can I run Ling 3.0 Flash Fin on 8 GB VRAM?

Only the IQ1_S quant (27.57 GB) can be loaded with 8 GB VRAM, but it will require additional CPU RAM for inference.

Does the model support image input?

No, Ling 3.0 Flash Fin only accepts text input and does not have vision capabilities.

What runtime is needed to run the model?

The model runs with llama.cpp (release b10776 or newer) and is compatible with vLLM and other llama.cpp‑based runtimes.

Other GGUFs of Ling-3.0-flash-Fin

Similar models

Browse all →

More from bartowski

All by bartowski →

More Ling models

All Ling →

Other large models

All large models →