llamaperf

Ling-3.0 VRAM requirements

Memory needed to run Ling-3.0 at every published size and quant, with an 8k context. Each figure is weights plus KV cache plus runtime buffers, from the same memory model as the VRAM calculator.

Total memory by size and quant

GB at an 8k context. Bold is the Q4_K_M column, the usual starting point.

SizeQ8_0Q6_KQ5_K_MQ4_K_MQ3_K_M
124B129106907559

KV cache by context length

GB the context alone adds on top of the weights. Add this to a weights figure to size a longer session.

SizeWeights at Q4_K_M4k ctx16k ctx32k ctx128k ctx
124B701.55.91247

What each size fits on at Q4_K_M

Hardware whose memory holds the model with headroom, smallest pool first. Fits means under 85% of the pool at an 8k context.

Frequently asked

How much VRAM does Ling-3.0 need?

About 75 GB at Q4_K_M with an 8k context for the 124B model, including the KV cache and runtime buffers. Q8 needs more and Q3 less; the table above lists every rung.

Can I run Ling-3.0 on a 16GB GPU?

Not comfortably. Even the 124B model needs about 75 GB at Q4_K_M with an 8k context, which is more than a 16 GB card holds with headroom. A lower quant or CPU offloading can still get it running, at a cost in quality or speed.

Can I run Ling-3.0 on a 24GB GPU such as an RTX 3090 or 4090?

Not comfortably. Even the 124B model needs about 75 GB at Q4_K_M with an 8k context, which is more than a 24 GB card holds with headroom.

How are these numbers calculated?

Weights at the quant's bits per weight, plus a KV cache sized from the model's attention design for the chosen context, plus compute buffers and a fixed runtime allowance. It is the same memory model the VRAM calculator uses. A family whose attention profile is not on file is sized as plain grouped-query attention, which errs towards needing more memory.