What Models?

Pick the right model for your GPU — in seconds.

Ling 3.1 Flash VRAM requirements: which GPUs can run it locally?

572.12B params 256K max context Tool useReasoning

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

QuantizationWeights16K context32K contextFull 256K
Q4_K_M333.4 GB333.6 GB333.7 GB335.9 GB
Q8_0566.6 GB566.8 GB566.9 GB569.2 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.cpp 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.cpp 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.

Apple

  • M3 Ultra 512 GB Q4_K_M 256K context · ~32 tok/s
  • M5 Ultra 512 GB Q4_K_M 256K context · ~45 tok/s
Check your exact setup in the full tool →