How much VRAM does DeepSeek V4 Flash 284B-A13B need?

At Q4_K_M the weights are 159.7 GB; with an 8K context KV cache and runtime overhead it needs 160.7 GB, so a 192 GB card runs it with headroom.

Can a GeForce RTX 4070 run DeepSeek V4 Flash 284B-A13B?

No — it does not fit even at the lowest quantisation.

Can a GeForce RTX 4090 run DeepSeek V4 Flash 284B-A13B?

No — it does not fit even at the lowest quantisation.

Can a GeForce RTX 3060 12 GB run DeepSeek V4 Flash 284B-A13B?

No — it does not fit even at the lowest quantisation.

Can a M3 Max · 64 GB run DeepSeek V4 Flash 284B-A13B?

No — it does not fit even at the lowest quantisation.

Hardware requirements

What hardware do I need to run DeepSeek V4 Flash 284B-A13B?

284B MoE · 13B active 1024K context MIT New this month

At Q4_K_M the weights are 159.7 GB; with an 8K KV cache and runtime overhead that is 160.7 GB, so it wants a 192 GB card to run with headroom — in practice 192 GB VRAM: Instinct MI300X. Every figure below is computed from the model’s published shape against each device’s usable memory; tokens per second are estimates. The method.

Minimum practical 141 GB VRAM

H200 SXM — Q3_K_M, 130.3 GB of 139.4 GB, ~189 tok/s, up to 201K context.

the smallest card that holds it at all, at Q3_K_M — the lowest quantisation worth running

Recommended 192 GB VRAM

Instinct MI300X — Q4_K_M, 160.7 GB of 190.4 GB, ~169 tok/s, up to 637K context.

runs the recommended quantisation with headroom at 8K context

High quality Nothing in the catalogue

No single device we list clears this bar — this is a multi-GPU or server-class model.

Long context Nothing in the catalogue

No single device we list clears this bar — this is a multi-GPU or server-class model.

Apple Silicon 256 GB unified

M3 Ultra · 256 GB — Q4_K_M, 160.7 GB of 192.0 GB, ~29 tok/s, up to 671K context.

smallest Mac that runs the recommended quantisation with headroom

CPU only 256 GB RAM

CPU only · DDR5 8-channel server — Q5_K_M, 188.4 GB of 204.8 GB, ~6.7 tok/s, up to 354K context.

no GPU — weights stream from system RAM

How much VRAM at each quantisation

Quant	Weights	+KV 8K	+KV 32K	+KV 128K	Total @ 8K	Needs	Quality
Q8_0	281.0 GB	0.38 GB	1.51 GB	6.0 GB	282.0 GB	no single card	−0.1% ppl
Q6_K	216.9 GB	0.38 GB	1.51 GB	6.0 GB	217.9 GB	no single card	−0.4% ppl
Q5_K_M	187.5 GB	0.38 GB	1.51 GB	6.0 GB	188.4 GB	no single card	−0.8% ppl
Q4_K_M	159.7 GB	0.38 GB	1.51 GB	6.0 GB	160.7 GB	192 GB card	−1.9% ppl
Q3_K_M	129.3 GB	0.38 GB	1.51 GB	6.0 GB	130.3 GB	192 GB card	−5.4% ppl
Q2_K	110.8 GB	0.38 GB	1.51 GB	6.0 GB	111.7 GB	141 GB card	−15% ppl

Totals add 0.6 GB runtime overhead and an f16 KV cache; "needs" is the smallest discrete card class whose usable memory (after display and driver reserve) leaves 15% headroom. A q8_0 cache roughly halves the KV columns.

Every device, checked

System RAM for offload:

16 32 64 128 256

NVIDIA · GeForce

Device	Memory	Best quant with headroom	Fits at all	Max context @ Q4_K_M	Tok/s est.	128K
GeForce RTX 5090	32 GB	—	no	—	—	no	Check
GeForce RTX 5080	16 GB	—	no	—	—	no	Check
GeForce RTX 5070 Ti	16 GB	—	no	—	—	no	Check
GeForce RTX 5070	12 GB	—	no	—	—	no	Check
GeForce RTX 5060 Ti 16 GB	16 GB	—	no	—	—	no	Check
GeForce RTX 5060	8 GB	—	no	—	—	no	Check
GeForce RTX 4090	24 GB	—	no	—	—	no	Check
GeForce RTX 4080 Super	16 GB	—	no	—	—	no	Check
GeForce RTX 4080	16 GB	—	no	—	—	no	Check
GeForce RTX 4070 Ti Super	16 GB	—	no	—	—	no	Check
GeForce RTX 4070 Ti	12 GB	—	no	—	—	no	Check
GeForce RTX 4070 Super	12 GB	—	no	—	—	no	Check
GeForce RTX 4070	12 GB	—	no	—	—	no	Check
GeForce RTX 4060 Ti 16 GB	16 GB	—	no	—	—	no	Check
GeForce RTX 4060 Ti	8 GB	—	no	—	—	no	Check
GeForce RTX 4060	8 GB	—	no	—	—	no	Check
GeForce RTX 3090 Ti	24 GB	—	no	—	—	no	Check
GeForce RTX 3090	24 GB	—	no	—	—	no	Check
GeForce RTX 3080 Ti	12 GB	—	no	—	—	no	Check
GeForce RTX 3080 12 GB	12 GB	—	no	—	—	no	Check
GeForce RTX 3080	10 GB	—	no	—	—	no	Check
GeForce RTX 3070 Ti	8 GB	—	no	—	—	no	Check
GeForce RTX 3070	8 GB	—	no	—	—	no	Check
GeForce RTX 3060 Ti	8 GB	—	no	—	—	no	Check
GeForce RTX 3060 12 GB	12 GB	—	no	—	—	no	Check
GeForce RTX 2080 Ti	11 GB	—	no	—	—	no	Check
GeForce RTX 2060 12 GB	12 GB	—	no	—	—	no	Check
GeForce GTX 1080 Ti	11 GB	—	no	—	—	no	Check

NVIDIA · GeForce laptop

Device	Memory	Best quant with headroom	Fits at all	Max context @ Q4_K_M	Tok/s est.	128K
GeForce RTX 5090 Laptop	24 GB	—	no	—	—	no	Check
GeForce RTX 4090 Laptop	16 GB	—	no	—	—	no	Check
GeForce RTX 4080 Laptop	12 GB	—	no	—	—	no	Check
GeForce RTX 4070 Laptop	8 GB	—	no	—	—	no	Check

NVIDIA · Workstation

Device	Memory	Best quant with headroom	Fits at all	Max context @ Q4_K_M	Tok/s est.	128K
RTX 6000 Ada	48 GB	—	no	—	—	no	Check
RTX 5000 Ada	32 GB	—	no	—	—	no	Check
RTX 4000 Ada	20 GB	—	no	—	—	no	Check
RTX 2000 Ada	16 GB	—	no	—	—	no	Check
RTX A6000	48 GB	—	no	—	—	no	Check
RTX A5000	24 GB	—	no	—	—	no	Check
RTX A4000	16 GB	—	no	—	—	no	Check

NVIDIA · Data centre

Device	Memory	Best quant with headroom	Fits at all	Max context @ Q4_K_M	Tok/s est.	128K
L40S	48 GB	—	no	—	—	no	Check
L4	24 GB	—	no	—	—	no	Check
A10	24 GB	—	no	—	—	no	Check
A100 40 GB	40 GB	—	no	—	—	no	Check
A100 80 GB	80 GB	—	offload	—	~5.6	no	Check
H100 PCIe	80 GB	—	offload	—	~5.6	no	Check
H100 SXM	80 GB	—	offload	—	~5.7	no	Check
H200 SXM	141 GB	—	Q3_K_M	—	—	no	Check
Tesla P40	24 GB	—	no	—	—	no	Check

AMD · Radeon

Device	Memory	Best quant with headroom	Fits at all	Max context @ Q4_K_M	Tok/s est.	128K
Radeon RX 9070 XT	16 GB	—	no	—	—	no	Check
Radeon RX 9070	16 GB	—	no	—	—	no	Check
Radeon RX 7900 XTX	24 GB	—	no	—	—	no	Check
Radeon RX 7900 XT	20 GB	—	no	—	—	no	Check
Radeon RX 7900 GRE	16 GB	—	no	—	—	no	Check
Radeon RX 7800 XT	16 GB	—	no	—	—	no	Check
Radeon RX 7700 XT	12 GB	—	no	—	—	no	Check
Radeon RX 7600 XT	16 GB	—	no	—	—	no	Check
Radeon RX 6900 XT	16 GB	—	no	—	—	no	Check
Radeon RX 6800 XT	16 GB	—	no	—	—	no	Check
Radeon RX 6700 XT	12 GB	—	no	—	—	no	Check

AMD · Radeon Pro

Device	Memory	Best quant with headroom	Fits at all	Max context @ Q4_K_M	Tok/s est.	128K
Radeon Pro W7900	48 GB	—	no	—	—	no	Check
Radeon Pro W7800	32 GB	—	no	—	—	no	Check

AMD · Instinct

Device	Memory	Best quant with headroom	Fits at all	Max context @ Q4_K_M	Tok/s est.	128K
Instinct MI210	64 GB	—	no	—	—	no	Check
Instinct MI300X	192 GB	Q4_K_M	Q5_K_M	637K	169	tight	Check

AMD · Ryzen AI Max

Device	Memory	Best quant with headroom	Fits at all	Max context @ Q4_K_M	Tok/s est.	128K
Ryzen AI Max+ 395 · 128 GB	128 GB	—	no	—	—	no	Check
Ryzen AI Max+ 395 · 64 GB	64 GB	—	no	—	—	no	Check

Apple · Apple Silicon

Device	Memory	Best quant with headroom	Fits at all	Max context @ Q4_K_M	Tok/s est.	128K
M1 · 16 GB	16 GB	—	no	—	—	no	Check
M1 Pro · 32 GB	32 GB	—	no	—	—	no	Check
M1 Max · 64 GB	64 GB	—	no	—	—	no	Check
M1 Ultra · 128 GB	128 GB	—	no	—	—	no	Check
M2 · 24 GB	24 GB	—	no	—	—	no	Check
M2 Pro · 32 GB	32 GB	—	no	—	—	no	Check
M2 Max · 96 GB	96 GB	—	no	—	—	no	Check
M2 Ultra · 192 GB	192 GB	—	Q3_K_M	—	—	no	Check
M3 · 24 GB	24 GB	—	no	—	—	no	Check
M3 Pro · 36 GB	36 GB	—	no	—	—	no	Check
M3 Max · 64 GB	64 GB	—	no	—	—	no	Check
M3 Max · 128 GB	128 GB	—	no	—	—	no	Check
M3 Ultra · 256 GB	256 GB	Q4_K_M	Q5_K_M	671K	29	tight	Check
M3 Ultra · 512 GB	512 GB	Q8_0	Q8_0	1024K	29	yes	Check
M4 · 32 GB	32 GB	—	no	—	—	no	Check
M4 Pro · 48 GB	48 GB	—	no	—	—	no	Check
M4 Pro · 64 GB	64 GB	—	no	—	—	no	Check
M4 Max · 64 GB	64 GB	—	no	—	—	no	Check
M4 Max · 128 GB	128 GB	—	no	—	—	no	Check

Intel · Arc

Device	Memory	Best quant with headroom	Fits at all	Max context @ Q4_K_M	Tok/s est.	128K
Arc B580	12 GB	—	no	—	—	no	Check
Arc B570	10 GB	—	no	—	—	no	Check
Arc A770 16 GB	16 GB	—	no	—	—	no	Check
Arc A750	8 GB	—	no	—	—	no	Check

CPU · CPU + system RAM

Device	Memory	Best quant with headroom	Fits at all	Max context @ Q4_K_M	Tok/s est.	128K
CPU only · DDR4 dual-channel	32 GB	—	no	—	—	no	Check
CPU only · DDR5 dual-channel	64 GB	—	no	—	—	no	Check
CPU only · DDR5 8-channel server	256 GB	Q4_K_M	Q5_K_M	942K	7.8	yes	Check