Ling 3.0 tiny
Ling 3.0 tiny is an open-weights language model from inclusionAI, released August 10, 2026. It has 7.9B parameters (mixture-of-experts, 1.4B active). The context window is 128K tokens.
Check it against your own PC →
Can you run Ling 3.0 tiny locally?
The smallest common GPU it runs on is 6 GB of VRAM (with 32 GB of RAM): Q6_K, GPU + experts in RAM, roughly 61 tokens per second. Estimates assume 32 GB of DDR5 RAM, a 16K context and llama.cpp-style GGUF quantization. Enter your exact hardware in the live app.
| GPU memory | Verdict | Best quant | VRAM | RAM | tok/s |
|---|---|---|---|---|---|
| 6 GB VRAM | Runs · GPU + CPU experts | Q6_K (≈ lossless) | 5.2 GB | 2.3 GB | ~61 |
| 8 GB VRAM | Runs on GPU | Q5_K_M (excellent) | 6.7 GB | – | ~140 |
| 12 GB VRAM | Runs on GPU | Q6_K (≈ lossless) | 7.5 GB | – | ~160 |
| 16 GB VRAM | Runs on GPU | Q6_K (≈ lossless) | 7.5 GB | – | ~210 |
| 24 GB VRAM | Runs on GPU | Q6_K (≈ lossless) | 7.5 GB | – | ~330 |
| 32 GB VRAM | Runs on GPU | Q6_K (≈ lossless) | 7.5 GB | – | ~490 |
Ready-made quantizations on Hugging Face: bloomer010/Ling-3.0-tiny-GGUF · bartowski/Ling-3.0-tiny-GGUF · maternion/ling3-tiny-coder-ckpts · SC117/Ling-3.0-tiny-abliterated-APEX-GGUF · NANI-Nithin/Ling-3.0-tiny-GGUF · WhiskyAKM/Ling-3.0-Tiny-GGUF
Benchmark results
Epoch AI has not published results for Ling 3.0 tiny yet. New models are usually evaluated within days to weeks.
Links
Hugging Face: inclusionAI/Ling-3.0-tiny
More from inclusionAI
Ling 3.1 flash 1019 · LBS 27B · Ling 3.0 flash Sante · Ling-1T · Ring-1T