Will Qwen2.5 Coder 32B Instruct run on my GPU?

32.5B parameters, 32,768-token context, Apache-2.0. At Q4_K_M the weights come to about 18.2 GiB; add 1.5 GiB for the runtime and you need roughly 19.7 GiB of VRAM before context.

Model card → Hosted pricing on PicksByModel →

Weights by quant

GiB

Q4_K_M · the everyday quant18.2 GiB

Q8_0 · near-lossless32.1 GiB

FP16 · full weights60.5 GiB

Runtime reserve1.5 GiB

Card by card

4 of 18 fit at Q4

Card	VRAM	Q4_K_M	Q8_0	FP16	Headroom at Q4	Buy
GeForce RTX 5090NVIDIA	32GB	Yes	Offload	Offload	12.3 GiB	$8,757 →
GeForce RTX 3090 (used)NVIDIA · used market	24GB	Yes	Offload	No	4.3 GiB	$2,404 →
GeForce RTX 4090 (used)NVIDIA · used market	24GB	Yes	Offload	No	4.3 GiB	$4,663 →
Radeon RX 7900 XTXAMD	24GB	Yes	Offload	No	4.3 GiB	$1,552 →
GeForce RTX 5060 Ti 16GBNVIDIA	16GB	Offload	No	No	short by 3.7 GiB	$1,146 →
GeForce RTX 5070 TiNVIDIA	16GB	Offload	No	No	short by 3.7 GiB	$1,792 →
GeForce RTX 5080NVIDIA	16GB	Offload	No	No	short by 3.7 GiB	$2,399 →
Radeon RX 7800 XTAMD	16GB	Offload	No	No	short by 3.7 GiB	$834 →
Radeon RX 9060 XT 16GBAMD	16GB	Offload	No	No	short by 3.7 GiB	$812 →
Radeon RX 9070AMD	16GB	Offload	No	No	short by 3.7 GiB	$1,052 →
Radeon RX 9070 XTAMD	16GB	Offload	No	No	short by 3.7 GiB	$1,194 →
Arc B580Intel	12GB	Offload	No	No	short by 7.7 GiB	$446 →
GeForce RTX 3060 12GB (used)NVIDIA · used market	12GB	Offload	No	No	short by 7.7 GiB	$588 →
GeForce RTX 4070 SuperNVIDIA · used market	12GB	Offload	No	No	short by 7.7 GiB	$1,156 →
GeForce RTX 5070NVIDIA	12GB	Offload	No	No	short by 7.7 GiB	$1,086 →
Arc B570Intel	10GB	Offload	No	No	short by 9.7 GiB	$299 →
GeForce RTX 5060NVIDIA	8GB	No	No	No	short by 11.7 GiB	$550 →
GeForce RTX 5060 Ti 8GBNVIDIA	8GB	No	No	No	short by 11.7 GiB	$809 →

Headroom is what remains for the KV cache after weights and the 1.5 GiB reserve. How far it stretches depends on the architecture: grouped-query models are frugal, older dense models are not. If the table says tight, plan on a shorter context or a lower quant. Parameter count from the model's own card. The Buy column opens live Amazon listings; those links may earn us a commission.

Will Qwen2.5 Coder 32B Instruct run on my GPU?

Weights by quant

Card by card

The Silicon Note