LLMs · Ant Group (inclusionAI)
Ling 3.0 Tiny (8B-A1.3B)
- Parameters
- 7.9B (1.3B active)
- Architecture
- Mixture of experts
- Max context
- 128K tokens
- License
- mit
- Released
- 2026-08
How to run it
Quantized files · GGUF
Works in LM Studio, llama.cpp, Jan and Ollama. No sign-in needed.
huggingface.co/inclusionAI/Ling-3.0-tiny-GGUF (opens in a new tab)
ollama run hf.co/inclusionAI/Ling-3.0-tiny-GGUFOriginal weights · Hugging Face
Full-precision files from Ant Group (inclusionAI), for fine-tuning, vLLM, Transformers.
huggingface.co/inclusionAI/Ling-3.0-tiny (opens in a new tab)
Memory needed
Weights plus KV cache and runtime overhead. Leave a little extra free for the operating system and other apps.
| Quantization | Quality | Weights | Total at 8K context | Total at 32K context | Download |
|---|---|---|---|---|---|
Q2_K |
Low | 3.2 GB | 4.0 GB | 4.7 GB | GGUF files (opens in a new tab) |
Q3_K_M |
Low | 3.9 GB | 4.7 GB | 5.4 GB | GGUF files (opens in a new tab) |
Q4_K_M |
Good | 4.8 GB | 5.6 GB | 6.3 GB | GGUF (opens in a new tab) |
Q5_K_M |
High | 5.6 GB | 6.4 GB | 7.1 GB | GGUF (opens in a new tab) |
Q6_K |
High | 6.5 GB | 7.3 GB | 8.0 GB | GGUF (opens in a new tab) |
Q8_0 |
Very high | 8.4 GB | 9.2 GB | 9.9 GB | GGUF (opens in a new tab) |
F16 |
Full | 15.8 GB | 16.6 GB | 17.3 GB | GGUF (opens in a new tab) Original weights (opens in a new tab) |
Best hardware for Ling 3.0 Tiny (8B-A1.3B)
The least expensive GPU in our catalog that runs it without offloading is the Intel Arc A380 (launch price $139) at Q4_K_M.
| Grade · points | Hardware | Quant | Memory | Speed | Fit |
|---|---|---|---|---|---|
| 82 ptsGreat (A) · 82 of 100 points: Model quality 27.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 | AMD Radeon RX 7900 XTX | F16 | 17.8 GB / 24.0 GB | 91.6 tok/s | Runs well |
| 82 ptsGreat (A) · 82 of 100 points: Model quality 27.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 | Apple M4 Pro (24 GB) | Q8_0 | 10.5 GB / 16.1 GB | 56.5 tok/s | Runs well |
| 82 ptsGreat (A) · 82 of 100 points: Model quality 27.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 | Intel Arc B580 | Q8_0 | 9.8 GB / 12.0 GB | 83.7 tok/s | Runs well |
| 82 ptsGreat (A) · 82 of 100 points: Model quality 27.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 | NVIDIA GeForce RTX 3090 | F16 | 17.8 GB / 24.0 GB | 104 tok/s | Runs well |
| 82 ptsGreat (A) · 82 of 100 points: Model quality 27.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 | NVIDIA GeForce RTX 4090 | F16 | 17.8 GB / 24.0 GB | 112 tok/s | Runs well |
| 82 ptsGreat (A) · 82 of 100 points: Model quality 27.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 | NVIDIA GeForce RTX 3060 12GB | Q8_0 | 9.8 GB / 12.0 GB | 86.5 tok/s | Runs well |
| 82 ptsGreat (A) · 82 of 100 points: Model quality 27.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 | NVIDIA GeForce RTX 4070 SUPER | Q8_0 | 9.8 GB / 12.0 GB | 121 tok/s | Runs well |
| 81 ptsGreat (A) · 81 of 100 points: Model quality 27.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 14.4/15 | AMD Radeon RX 9070 XT | Q8_0 | 10.0 GB / 16.0 GB | 132 tok/s | Runs well |
| 81 ptsGreat (A) · 81 of 100 points: Model quality 27.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 14.4/15 | NVIDIA GeForce RTX 4060 Ti 16GB | Q8_0 | 10.0 GB / 16.0 GB | 69.2 tok/s | Runs well |
| 81 ptsGreat (A) · 81 of 100 points: Model quality 27.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 14.4/15 | NVIDIA GeForce RTX 4070 Ti SUPER | Q8_0 | 10.0 GB / 16.0 GB | 162 tok/s | Runs well |
Estimates come from published hardware specs and our open formulas, not from running the model on your machine. Real speed varies with runtime, drivers and settings. Numbers marked “Measured” come from a linked benchmark.