Card × model estimate

Qwen2.5 Coder 14B on RTX 4080 SUPER Q4_K_M

should fit

On an RTX 4080 SUPER (16 GB), Qwen2.5 Coder 14B in Q4_K_M needs about 9,9 Go of video memory: it should fit.

Not measured yet: the figures below are estimates, computed from the models already measured on this card. Measure my card

—

Generation (estimated)

≥ 9,9 Go

Recommended VRAM (16 GB avail.)

—

Power (ref. model)

—

Electricity / M tokens · 0,25 €/kWh

No model has been measured on the RTX 4080 SUPER yet: no speed estimate possible.

What about a longer context?

Context	KV cache	Estimated VRAM	Fits in 16 GB?	Estimated speed
4 096	0,8 Go	9,6 Go	yes	—
8 192	1,5 Go	10,4 Go	yes	—
16 384	3,0 Go	11,9 Go	yes	—
32 768	6,0 Go	14,9 Go	yes	—

Estimated VRAM = file + KV cache (full-attention layers, f16) + ~0,5 Go of buffers, excluding memory used by the system — hence the slightly higher “recommended VRAM”, which keeps that margin. Speed ≈ estimated speed × weights read ÷ (weights read + added KV cache).

Qwen2.5 Coder 14B on other cards

should fit

Qwen2.5 Coder 14B page RTX 4080 SUPER page Feel the speed Download the GGUF (8,4 Go)

Estimates based on real measurements of other models on this card and on the model's public data (Qwen). As soon as a measurement exists, this page shows the real figures.