LLMs · Ant Group (inclusionAI)
Ling 3.0 Flash (127B-A5B)
- Parameters
- 127B (5.1B active)
- Architecture
- Mixture of experts
- Max context
- 256K 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-flash-GGUF (opens in a new tab)
ollama run hf.co/inclusionAI/Ling-3.0-flash-GGUFOriginal weights · Hugging Face
Full-precision files from Ant Group (inclusionAI), for fine-tuning, vLLM, Transformers.
huggingface.co/inclusionAI/Ling-3.0-flash (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 | 51.0 GB | 52.0 GB | 53.2 GB | GGUF files (opens in a new tab) |
Q3_K_M |
Low | 62.5 GB | 63.5 GB | 64.7 GB | GGUF files (opens in a new tab) |
Q4_K_M |
Good | 77.8 GB | 78.8 GB | 80.0 GB | GGUF · folder (opens in a new tab) |
Q5_K_M |
High | 90.5 GB | 91.5 GB | 92.7 GB | GGUF · folder (opens in a new tab) |
Q6_K |
High | 105 GB | 106 GB | 107 GB | GGUF · folder (opens in a new tab) |
Q8_0 |
Very high | 135 GB | 136 GB | 137 GB | GGUF · folder (opens in a new tab) |
F16 |
Full | 255 GB | 256 GB | 257 GB | GGUF · folder (opens in a new tab) Original weights (opens in a new tab) |
Best hardware for Ling 3.0 Flash (127B-A5B)
The least expensive GPU in our catalog that runs it without offloading is the NVIDIA RTX PRO 6000 Blackwell (launch price $8,565) at Q4_K_M.
| Grade · points | Hardware | Quant | Memory | Speed | Fit |
|---|---|---|---|---|---|
| 91 ptsExcellent (S) · 91 of 100 points: Model quality 36.9/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 | Apple M3 Ultra (256 GB) | Q8_0 | 151 GB / 192 GB | 43.2 tok/s | Runs well |
| 91 ptsExcellent (S) · 91 of 100 points: Model quality 36.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 | Apple M2 Ultra (192 GB) | Q6_K | 117 GB / 144 GB | 57.5 tok/s | Runs well |
| 89 ptsExcellent (S) · 89 of 100 points: Model quality 35.1/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15 | Apple M4 Max (128 GB) | Q4_K_M | 86.4 GB / 96.0 GB | 56.6 tok/s | Tight fit |
| 89 ptsExcellent (S) · 89 of 100 points: Model quality 35.1/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15 | NVIDIA RTX PRO 6000 Blackwell | Q4_K_M | 83.6 GB / 96.0 GB | 216 tok/s | Tight fit |
| 88 ptsExcellent (S) · 88 of 100 points: Model quality 35.1/45, Memory fit 25.0/25, Speed 13.6/15, Memory use 15.0/15 | NVIDIA GB10 (128 GB) | Q4_K_M | 88.0 GB / 115 GB | 32.9 tok/s | Runs well |
| 86 ptsExcellent (S) · 86 of 100 points: Model quality 36.9/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 10.0/15 | Apple M3 Ultra (512 GB) | Q8_0 | 167 GB / 384 GB | 43.2 tok/s | Runs well |
| 86 ptsExcellent (S) · 86 of 100 points: Model quality 35.1/45, Memory fit 24.0/25, Speed 12.2/15, Memory use 15.0/15 | AMD Ryzen AI Max+ 395 (128 GB) | Q4_K_M | 86.4 GB / 96.0 GB | 26.5 tok/s | Tight fit |
| 59 ptsGood (B) · 59 of 100 points: Model quality 25.8/45, Memory fit 4.0/25, Speed 15.0/15, Memory use 15.0/15 | Apple M1 Max (64 GB) | Q2_K | 55.8 GB / 48.0 GB | 57.9 tok/s | Heavy offload |
| 59 ptsGood (B) · 59 of 100 points: Model quality 25.8/45, Memory fit 4.0/25, Speed 15.0/15, Memory use 15.0/15 | Apple M4 Max (64 GB) | Q2_K | 55.8 GB / 48.0 GB | 79.0 tok/s | Heavy offload |
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.