How much VRAM does DeepSeek-V4-Flash-162B need?

Q2_K is exactly 59,153,122,976 bytes (55.09 GiB) in weights. Add the KV cache, which depends on context length, plus roughly half a gigabyte of runtime overhead.

Is DeepSeek-V4-Flash-162B a mixture-of-experts model?

Yes — 144 experts with 6 routed per token. Every expert must be resident in memory, but only the routed ones are read per token, so its memory requirement and its speed behave very differently.

0xSero · text · mixture of experts

DeepSeek-V4-Flash-162B

0xSero/DeepSeek-V4-Flash-162B

DeepSeek-V4-Flash-162B at Q2_K is exactly 59,153,122,976 bytes (55.09 GiB / 59.15 GB) — an effective 5.135 bits per weight, not the nominal 2.

From the file· summed from 1 file(s)From the file· KV per layer

Parameters

92.2B

total, not active

Architecture

deepseek4

43 layers

Context

1,048,576

native (config.json)

License

mit

Shipped quantizations

● exact bytes, summed from published files

Quant	Size●	Exact bytes●	Effective bpw●	Tensors●	Publisher
Q2_K	55.09 GiB	59,153,122,976	5.135	—	xik94
Q3_K_M	72.27 GiB	77,601,530,528	6.736	—	xik94

KV cache by context

unresolved

This model declares a 128-token sliding window, but we could not establish which layers use it. Its architecture publishes the layout as a per-layer array inside the model file rather than as a period in config.json, and we have not yet ingested that array.

A flat context × layers × heads figure would be substantially too high, so we are not showing one. This is tracked as a known gap rather than filled with a guess.

Compare with

same modality, comparable size

vs Qwen3-Coder-30B-A3B-Instruct vs Qwen3.6-27B vs Qwen3.8-27B vs DeepSeek-V4-Flash vs Qwen3-30B-A3B-Thinking-2507 vs Laguna-XS-2.1 All alternatives →Will it fit on my card? →

Why other calculators give a different number

A parameters × bits ÷ 8 estimate puts Q2_K at roughly 48.28 GiB. The real file is 55.09 GiB, because a quantization is a mixture and some tensors are always kept at higher precision.

Architecture

from config.json

Layers

Attention heads

KV heads

Head dim

512

Hidden size

4096

Vocab

129,280

Sliding window

128

SWA period

—

MLA

Experts

144

Experts per token

use_sliding_window

—

Questions people ask

How much VRAM does DeepSeek-V4-Flash-162B need?: Q2_K is exactly 59,153,122,976 bytes (55.09 GiB) in weights. Add the KV cache, which depends on your context length, plus roughly half a gigabyte of runtime overhead.
Is DeepSeek-V4-Flash-162B a mixture-of-experts model?: Yes — 144 experts, 6 routed per token. Every expert must be resident, but only the routed ones are read per token, which is why its memory requirement and its speed behave very differently.
Which quantization of DeepSeek-V4-Flash-162B should I use?: Q4_K_M is the usual default. Pick the largest quantization that fits your card at the context you actually need — the table above gives exact sizes for every one published.