LI

Ling 3.0 Flash Dspark

LingGGUF by bloomer010Updated 2026-09-20
Download on Hugging Face
Parameters127B
Context256K
Layers5
Architecturedflash
Smallest quant0.5 GB
Quick answer

Ling 3.0 Flash Dspark 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 22 quants, from 0.5 GB (Q2_K) to 255.1 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 2.7 GB.

Ling 3.0 Flash Dspark – 130B hybrid linear model in GGUF format

Ling 3.0 Flash Dspark is a 130‑billion‑parameter hybrid linear model with 262,144‑token context. It is available in multiple GGUF quantizations, ranging from Q2_K to Q8_K_XL. The model is licensed under MIT and is designed for production agentic workloads.

Good at

  • Long‑context reasoning
  • Agentic tool calling
  • High‑throughput inference

Limits

  • Requires large VRAM for higher‑precision quants
  • No vision support
  • No separate drafter file needed

Best for

  • Complex agent workflows
  • Long‑horizon coding tasks
  • Production inference on GPUs

Who it’s for. Developers and researchers needing a large, efficient hybrid linear model for agentic and long‑context tasks. The model is suitable for deployment in production environments that support llama.cpp and the required parser PRs.

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 →
BF161.9 GB 3.1 GB
Fits Get file →
Q1_019.5 GB 20.6 GB
Too big Get file →
IQ1_S26.7 GB 27.9 GB
Too big Get file →
IQ1_M29.5 GB 30.7 GB
Too big Get file →
IQ2_M42.1 GB 43.3 GB
Too big Get file →
Q2_K_XL43.4 GB 44.6 GB
Too big Get file →
IQ3_XXS51.2 GB 52.4 GB
Too big Get file →
Q3_K_M62.6 GB 63.7 GB
Too big Get file →
Q3_K_XL62.6 GB 63.8 GB
Too big Get file →
MXFP4_MOE69.8 GB 71.0 GB
Too big Get file →
Q4_K_S73.9 GB 75.1 GB
Too big Get file →
Q4_K_M78.3 GB 79.5 GB
Too big Get file →
Q4_K_XL84.7 GB 85.9 GB
Too big Get file →
Q5_K_S89.0 GB 90.2 GB
Too big Get file →
Q5_K_M91.5 GB 92.7 GB
Too big Get file →
Q6_K105.5 GB 106.7 GB
Too big Get file →
Q6_K_XL115.6 GB 116.8 GB
Too big Get file →
Q8_0135.6 GB 136.8 GB
Too big Get file →
Q8_K_XL177.1 GB 178.3 GB
Too big Get file →
BF16255.1 GB 256.3 GB
Too big Get file →

For 8 GB VRAM, use Q4_K_M (1.8 GB memory at 8 k context). For 16 GB VRAM, Q4_K_XL (85.9 GB memory estimate) is suitable. If GPU memory is limited, consider Q2_K (1.7 GB estimate) and keep experts on CPU.

What GPU do you need for Ling 3.0 Flash Dspark?

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 Q1_0 (19.5 GB file, about 20.6 GB in use).
  • 32 GB VRAM: the best quant that fits is IQ1_M (29.5 GB file, about 30.7 GB in use).
  • 48 GB VRAM: the best quant that fits is Q2_K_XL (43.4 GB file, about 44.6 GB in use).

Which Ling 3.0 Flash Dspark quant should you choose?

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

The Q8_0 file is 135.6 GB, about 204.1 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
Parameters127B
Layers5
Trained context262,144 tokens
KV cache (fp16)80 KB per token

Source

Quantized bybloomer010
FamilyLing
Licensemit
Downloads (HF)74,290
Last updated2026-09-20

Frequently asked questions about Ling 3.0 Flash Dspark

How much VRAM does Ling 3.0 Flash Dspark 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 Dspark 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 Dspark GGUF?

It depends on the quant: Q2_K is 0.5 GB, Q4_K_M is 0.7 GB, BF16 is 1.9 GB, Q1_0 is 19.5 GB, IQ1_S is 26.7 GB, IQ1_M is 29.5 GB and 16 more.

What context length does Ling 3.0 Flash Dspark 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 Dspark GGUF?

The files are on Hugging Face in the bloomer010/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 Dspark 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 Dspark on 8 GB VRAM?

Yes, using the Q4_K_M quant which requires approximately 1.8 GB of VRAM at 8 k context.

Does the model support vision?

No, Ling 3.0 Flash Dspark does not include vision capabilities.

What is the recommended sampling setting?

Use temperature 0.6, top_p 0.95, top_k 20 with thinking mode enabled by default.

Other GGUFs of Ling-3.0-flash

Similar models

Browse all →

More from bloomer010

All by bloomer010 →

More Ling models

All Ling →

Other large models

All large models →