DeepSeek V4.1 — local AI model by DeepSeek

Written by Jakub Rusinowski · Last updated

DeepSeek V4.1 — the Flash member shipped 10 September 2026 under MIT with an encoder-decoder design and native image input. A V4.1 Pro was announced without a date and had not shipped as of September 2026.

Hugging Face DeepSeek API Docs

Variants

The smallest DeepSeek V4.1 variant needs about 172 GB of VRAM at Q4 (experimental) — quantized weights plus framework overhead, before any KV cache.

ModelVRAM
DeepSeek V4.1 Flash →
284B (13B active)
~172.3 GB
DeepSeek V4.1
1.6T (49B active)
~966.8 GB

Memory is quantized weights plus overhead at Q4_K_M, from the same engine as the GPU & VRAM checker.

How to run DeepSeek V4.1 locally

Install Ollama, then pull the tag.

ollama run deepseek-v4-1

Pick a size above for its own VRAM figure, speed estimate and install command.

Licence

MITCommercial use permitted

Commercial use permitted. No usage restrictions beyond attribution.

Applies to: DeepSeek V4.1 Flash, DeepSeek V4.1

Recommended GPU

The cheapest catalogued GPU that runs DeepSeek V4.1 locally (min 172 GB VRAM) is the Apple M2 Ultra (192 GB).

Affiliate disclosure: Some links on this page are affiliate links — if you buy through them, LLM Configurator may earn a commission at no extra cost to you. As an Amazon Associate, LLM Configurator earns from qualifying purchases.
Apple Mac Studio M2 Ultra
192 GB VRAM · 60 W board power
2026 prices are volatile — check the current listing.

Can I run DeepSeek V4.1 on my GPU?

DeepSeek V4.1 — frequently asked questions

How much VRAM does DeepSeek V4.1 need?

DeepSeek V4.1 needs about 172 GB VRAM at Q4 (experimental) quantization for its smallest variant. Variants: DeepSeek V4.1 Flash (172 GB, Q4 (experimental)); DeepSeek V4.1 (967 GB, Q4 (experimental, datacenter only)). On Apple Silicon, unified memory counts toward this requirement.

Can I run DeepSeek V4.1 on an RTX 4090 (24 GB)?

DeepSeek V4.1's smallest variant needs about 172 GB, which exceeds a single RTX 4090 (24 GB). Use multiple GPUs, a higher-VRAM card, or Apple Silicon with large unified memory.

What quantization should I use for DeepSeek V4.1?

Q4_K_M is the best balance of quality and VRAM for DeepSeek V4.1 in most cases. Choose Q8_0 for near-lossless quality if you have spare VRAM, or smaller quants (Q3/Q2) only when memory is tight.

How do I run DeepSeek V4.1 with Ollama?

DeepSeek V4.1 has no local Ollama tag — the published tag is cloud-hosted, so running it sends your prompts to a hosted GPU rather than your own machine.