Card × model estimate

R1 Distill 32B Qwen on RTX 5090 Q4_K_M

should fit

On an RTX 5090 (32 GB), R1 Distill 32B Qwen in Q4_K_M needs about 20,0 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)

≥ 20,0 Go

Recommended VRAM (32 GB avail.)

—

Power (ref. model)

—

Electricity / M tokens · 0,25 €/kWh

No model has been measured on the RTX 5090 yet: no speed estimate possible.

What about a longer context?

Context	KV cache	Estimated VRAM	Fits in 32 GB?	Estimated speed
4 096	1,0 Go	20,0 Go	yes	—
8 192	2,0 Go	21,0 Go	yes	—
16 384	4,0 Go	23,0 Go	yes	—
32 768	8,0 Go	27,0 Go	yes	—
65 536	16,0 Go	35,0 Go	no	—
131 072	32,0 Go	51,0 Go	no	—

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).

R1 Distill 32B Qwen on other cards

should fit

R1 Distill 32B Qwen page RTX 5090 page Feel the speed Download the GGUF (18,5 Go)

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