LI

Ling 3.0 flash VL

LingGGUF by bloomer010Updated 2026-09-26
Download on Hugging Face
Parameters124B
Context256K
Layers5
Architecturedflash
Smallest quant0.5 GB
Quick answer

Ling 3.0 flash VL needs about 1.8 GB of memory at Q4_K_M (a 0.7 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 21 quants, from 0.5 GB (Q2_K) to 248.9 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 2.7 GB.

Ling 3.0 flash VL – 120 B multimodal model with 256K token context

Ling 3.0 flash VL is a 120 B multimodal model that supports image and video inputs. It offers a 256K token context window and 5.5 B activated parameters per token. The model is released under the MIT license.

Good at

  • Vision and text multimodal reasoning
  • Long‑context dialogue up to 256K tokens
  • Video understanding with VideoRoPE

Limits

  • Requires bundled mmproj-model-f16.gguf for vision
  • Large VRAM needed for higher‑precision quants
  • No text‑only support without the vision file

Best for

  • Multimodal chat with images and videos
  • Long‑form multimodal content creation
  • Agentic workflows that combine vision and text

Who it’s for. Developers building multimodal applications that need both vision and long‑context language understanding. The model is suitable for research and production use under the MIT license.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K0.5 GB 1.7 GB
Fits Get file →
Q4_K_M0.7 GB 1.8 GB
Fits Get file →
Q6_K0.8 GB 2.0 GB
Fits Get file →
BF161.9 GB 3.1 GB
Fits Get file →
IQ2_XS36.5 GB 37.7 GB
Too big Get file →
IQ2_M40.6 GB 41.8 GB
Too big Get file →
Q2_K_XL41.9 GB 43.1 GB
Too big Get file →
Q3_K_M59.3 GB 60.5 GB
Too big Get file →
Q3_K_XL60.6 GB 61.8 GB
Too big Get file →
MXFP4_MOE68.2 GB 69.3 GB
Too big Get file →
Q4_K_S70.7 GB 71.8 GB
Too big Get file →
Q4_K_M75.3 GB 76.4 GB
Too big Get file →
Q4_K_XL81.9 GB 83.1 GB
Too big Get file →
Q5_K_M88.3 GB 89.5 GB
Too big Get file →
Q5_K_XL92.3 GB 93.5 GB
Too big Get file →
Q6_K102.2 GB 103.4 GB
Too big Get file →
Q6_K_XL103.1 GB 104.3 GB
Too big Get file →
Q6_K112.8 GB 114.0 GB
Too big Get file →
Q8_0132.4 GB 133.5 GB
Too big Get file →
Q8_K_XL172.5 GB 173.6 GB
Too big Get file →
BF16248.9 GB 250.1 GB
Too big Get file →

For 8 GB VRAM, use Q4_K_M (0.66 GB, ~1.8 GB memory at 8K context). For 16 GB VRAM, Q6_K (0.8 GB, ~2 GB memory) or Q4_K_S (70.67 GB, ~71.8 GB memory) if you can offload to CPU. Higher‑precision quants such as BF16 require more than 32 GB VRAM.

What GPU do you need for Ling 3.0 flash VL?

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: the best quant that fits is BF16 (1.9 GB file, about 3.1 GB in use).
  • 6 GB VRAM: the best quant that fits is BF16 (1.9 GB file, about 3.1 GB in use).
  • 8 GB VRAM: the best quant that fits is BF16 (1.9 GB file, about 3.1 GB in use).
  • 12 GB VRAM: the best quant that fits is BF16 (1.9 GB file, about 3.1 GB in use).
  • 16 GB VRAM: the best quant that fits is BF16 (1.9 GB file, about 3.1 GB in use).
  • 24 GB VRAM: the best quant that fits is BF16 (1.9 GB file, about 3.1 GB in use).
  • 32 GB VRAM: the best quant that fits is BF16 (1.9 GB file, about 3.1 GB in use).
  • 48 GB VRAM: the best quant that fits is Q2_K_XL (41.9 GB file, about 43.1 GB in use).

Which Ling 3.0 flash VL quant should you choose?

Q4_K_M is the usual starting point for Ling 3.0 flash VL: it balances file size and quality well. Here it is a 0.7 GB file.

The Q8_0 file is 132.4 GB, about 199.2 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 Q2_K at 0.5 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturedflash
Parameters124B
Layers5
Trained context262,144 tokens
KV cache (fp16)80 KB per token

Source

Quantized bybloomer010
FamilyLing
Licensemit
Downloads (HF)3,351
Last updated2026-09-26

Frequently asked questions about Ling 3.0 flash VL

How much VRAM does Ling 3.0 flash VL need?

About 1.8 GB at Q4_K_M with an 8K context window. That is the 0.7 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 VL on an 8 GB GPU?

Yes, with BF16: the 1.9 GB file needs about 3.1 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Ling 3.0 flash VL GGUF?

It depends on the quant: Q2_K is 0.5 GB, Q4_K_M is 0.7 GB, Q6_K is 0.8 GB, BF16 is 1.9 GB, IQ2_XS is 36.5 GB, IQ2_M is 40.6 GB and 15 more.

What context length does Ling 3.0 flash VL support?

The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 0.7 GB at 8K and 2.7 GB at 32K.

Where can I download Ling 3.0 flash VL GGUF?

The files are on Hugging Face in the bloomer010/Ling-3.0-flash-VL-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 VL 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 VL on 8 GB VRAM?

Yes, with the Q4_K_M quant (0.66 GB file) which uses about 1.8 GB memory at 8K context. Ensure the bundled vision file is present.

Do I need the mmproj-model-f16.gguf file for text‑only chat?

No, text‑only chat works without the vision file, but the file is required for any image or video input.

What is the context window size of this model?

The model supports up to 256K tokens in the context window.

Other GGUFs of Ling-3.0-flash-VL

Similar models

Browse all →

More from bloomer010

All by bloomer010 →

More Ling models

All Ling →

Other large models

All large models →