Can I Run DeepSeek V4-Flash on AMD Ryzen AI Max+ 395?

Name: LLM Configurator — GPU VRAM Checker
Author: LLM Configurator

作者： Jakub Rusinowski · 最后更新： 2026年8月15日

Not at Q4 (experimental) — that needs 171.5 GB and the AMD Ryzen AI Max+ 395 has 96 GB. Drop to Q2_K and it fits in 94.7 GB, with up to 8K of context.

The numbers

Model	DeepSeek V4-Flash
Parameters	284B (13B active)
Quantization	Q4 (experimental)
VRAM needed	171.5 GB
AMD Ryzen AI Max+ 395 VRAM	96 GB
Verdict	Runs at a lower quant
Fits at	Q2_K (94.7 GB)
Max context	8K

What to do next

Quantize to Q2_K. That is the cheapest fix — it costs some quality but no money.

联盟营销声明: 本页部分链接为联盟推广链接——如果你通过它们购买，LLM Configurator 可能会获得佣金，而你无需支付任何额外费用。作为亚马逊联盟成员（Amazon Associate），LLM Configurator 会从符合条件的购买中获得收益。

Running DeepSeek V4-Flash on this card:

Ryzen AI Max+ 395 Laptop (Strix Halo, up to 128GB)

96 GB VRAM · 120 W board power

2026年价格波动较大——请以当前商品页价格为准。

在亚马逊查看价格

Won't fit — rent DeepSeek V4-Flash instead

DeepSeek V4-Flash needs ~171 GB but this GPU has 96 GB. Rent a 8× H100 (640 GB)-class GPU by the hour instead of buying one:

Affiliate links — we may earn a commission if you sign up, at no extra cost to you.

RunPod $23.12/hr

Rent on RunPod →

Cloud rates verified 2026-07 — estimates, and marketplace prices vary. Buying price is GPU MSRP only, not a full PC.

Other DeepSeek V4 sizes on the AMD Ryzen AI Max+ 395

DeepSeek V4-Pro — does not fit (526.0 GB)

DeepSeek V4-Flash on nearby hardware

NVIDIA H100 80GB (80 GB) — does not fit
Apple M4 Max (128 GB) — runs at a lower quant

All DeepSeek V4 sizes on the AMD Ryzen AI Max+ 395 | VRAM calculator for DeepSeek V4-Flash | AMD Ryzen AI Max+ 395 GPU page | Check your hardware