Ling 3.1 Flash VRAM requirements: which GPUs can run it locally?
The smallest GPU memory that runs Ling 3.1 Flash well is 512 GB (Q4_K_M, e.g. M3 Ultra). 2 of 132 GPUs run it well. It's a mixture-of-experts model, so all weights must fit in memory but speed depends only on the active experts.
VRAM needed per quantization
| Quantization | Weights | 16K context | 32K context | Full 256K |
|---|---|---|---|---|
| Q4_K_M | 333.4 GB | 333.6 GB | 333.7 GB | 335.9 GB |
| Q8_0 | 566.6 GB | 566.8 GB | 566.9 GB | 569.2 GB |
Weights plus fp16 KV cache. Leave ~1 GB headroom for the inference engine.
Run it locally
Each command downloads the GGUF from Hugging Face, then Ollama starts a chat and llama.cpp starts an OpenAI-compatible server with a web UI on port 8080.
llama-server -hf bartowski/Ling-3.1-flash-1019-GGUF:Q4_K_M Split into 10 files, which Ollama can't pull from Hugging Face yet; llama.cpp downloads the whole set.
llama-server -hf bartowski/Ling-3.1-flash-1019-GGUF:Q8_0 Split into 16 files, which Ollama can't pull from Hugging Face yet; llama.cpp downloads the whole set.
GPUs that can run Ling 3.1 Flash
Best quantization that fits on each GPU, with the context and speed it gets. For chips with several memory sizes, the smallest that works is shown.