DeepSeek V4 is the most capable model ever released under MIT license. V4-Pro at 1.6T parameters and V4-Flash at 284B both ship with open weights on Hugging Face, meaning you can run frontier-adjacent AI on your own infrastructure with zero vendor lock-in. The question isn't whether you can self-host it, it's whether you should, and what hardware you need.

V4-Flash needs roughly 170-175GB of total VRAM (158GB weights + ~10GB for the full 1M KV cache + overhead) and fits comfortably on 2x H200 or 2x RTX Pro 6000 Blackwell. V4-Pro at ~862GB needs a real GPU cluster. Both require careful deployment planning to get right. This guide covers hardware requirements, vLLM setup, quantization options, expert parallelism, cost analysis, and production deployment patterns.

If you're evaluating self-hosting vs API for DeepSeek V4, this is the guide that gives you the numbers to make that decision.

1Why Self-Host DeepSeek V4?

Three reasons make self-hosting V4 compelling:

• Data sovereignty: DeepSeek's hosted API routes through Chinese infrastructure. For regulated industries, defense contractors, or teams with strict data residency requirements, self-hosting on your own cloud eliminates this concern entirely.
• Cost at scale: At very high token volumes (several billion tokens/day), self-hosting V4-Flash can be cheaper than DeepSeek's API. You pay for GPU hours, not per-token. See the break-even math in section 9 before assuming this applies to you.
• Customization: MIT license means you can fine-tune V4 for your domain, modify the inference pipeline, and integrate it into custom toolchains without restrictions.

The trade-off: self-hosting requires GPU infrastructure expertise, ongoing maintenance, and upfront capital. For teams below multi-billion tokens/day, the API is almost always more cost-effective. Run the math in section 9 against your actual traffic before committing.

2Hardware Requirements: V4-Flash vs V4-Pro

3Downloading Weights from Hugging Face

Both models are available on Hugging Face under the deepseek-ai organization. The Instruct checkpoints (FP4+FP8 mixed precision) are what you want for production deployment:

4vLLM Deployment Setup

vLLM is the recommended inference framework for DeepSeek V4. It supports MoE expert parallelism, the hybrid CSA+HCA attention architecture, and efficient KV cache management for 1M-token contexts.

The vLLM server exposes an OpenAI-compatible API, so you can point any existing OpenAI SDK client at it by changing the base URL. This makes migration from the DeepSeek hosted API to self-hosted seamless.

5Expert Parallelism & Tensor Parallelism

MoE models like V4 benefit from two types of parallelism:

• Tensor Parallelism (TP): Splits individual layers across GPUs. Use this when a single layer's weights don't fit in one GPU's VRAM. Set --tensor-parallel-size to the number of GPUs.
• Expert Parallelism (EP): Distributes different expert sub-networks across GPUs. Since MoE only activates a subset of experts per token, EP allows efficient utilization of multi-GPU setups without the communication overhead of TP.

For V4-Flash on 4x A100 or 2x H200, tensor parallelism alone is sufficient. For V4-Pro on 8+ GPUs, a combination of TP and EP gives the best throughput. vLLM handles this automatically when you set the appropriate parallelism flags.

6Quantization Options: FP8, FP4, INT4

DeepSeek ships V4 in two precision formats:

• FP8 Mixed (Base checkpoints): Most parameters in FP8 precision. Higher quality, larger memory footprint.
• FP4+FP8 Mixed (Instruct checkpoints): MoE expert parameters in FP4, other parameters in FP8. This is the recommended format: it balances quality and memory usage.

For further compression, community quantizations (GGUF, AWQ, GPTQ) will likely appear within days of launch. INT4 quantization can reduce V4-Flash to ~80GB, potentially fitting on 4x RTX 4090 (96GB total), but expect measurable quality degradation, especially on reasoning-heavy tasks.

71M Context Window Configuration

V4's hybrid CSA+HCA attention reduces KV cache to roughly 7% of V3.2's footprint at 1M context. In practice, a full 1M-token context consumes about 10GB of VRAM on top of the 158GB of weights, plus a few GB of runtime overhead. Total: roughly 170-175GB.

For V4-Flash, that fits on 2x H200 (282GB) or 2x RTX Pro 6000 Blackwell (192GB) with plenty of headroom. On A100 80GB, 2 cards give you only 160GB, which is below the budget once you load the full KV cache. Four A100s (320GB) are the next power-of-two tensor parallel size that vLLM supports, which is why most vLLM guides recommend 4x A100 80GB. The headroom is incidental, not required.

Set --max-model-len in vLLM to your desired context length. Start with 131072 (128K) and increase based on your VRAM headroom. Monitor GPU memory usage during inference to find the sweet spot for your hardware.

8AWS Deployment: Instance Types & Costs

With 1-year reserved instances, costs drop roughly 40%. Spot instances can reduce costs further but aren't suitable for production inference due to interruption risk. Pricing varies by region and changes often, so always check the AWS pricing page before budgeting. For most teams, a single p5.48xlarge running V4-Flash is the cost-effective starting point.

9Self-Host vs API: Break-Even Analysis

The honest answer is that pure-cost break-even against DeepSeek's own API is hard to reach. Here is the math for V4-Flash using AWS us-east-1 on-demand pricing:

• API cost: $0.14/M input, $0.28/M output (cache miss). Blended 50/50 input/output rate is roughly $0.21/M. At 50M tokens/day, that is about $7-$14/day depending on the mix.
• Self-host cost: p5.48xlarge at $55.04/hr on-demand is about $1,321/day. A 1-year reserved instance at roughly 40% off drops that to around $790/day.
• Break-even: To match $790/day of API spend at $0.21/M, you need to serve roughly 3.8 billion tokens/day on one reserved p5.48xlarge. A single 8x H100 node cannot physically sustain that throughput for V4-Flash, so the math almost never favors self-hosting on price alone for a single workload.

For all but the largest serving operations, DeepSeek's API is cheaper. Self-hosting is the right call when data sovereignty, regulatory residency, custom fine-tuning, or consistent latency under unpredictable API quotas outweigh raw cost. Those are legitimate reasons, but they are not a cost argument.

10Why Lushbinary for LLM Infrastructure

Lushbinary deploys self-hosted LLMs on AWS for teams that need data sovereignty, custom fine-tuning, or cost optimization at scale. We handle the full infrastructure stack: GPU instance selection, vLLM configuration, auto-scaling, monitoring, and cost optimization.

❓ Frequently Asked Questions

Sources

• DeepSeek V4-Flash Model Card on Hugging Face
• DeepSeek V4-Pro Model Card on Hugging Face
• DeepSeek V4 Developer Guide on Lushbinary

Content was rephrased for compliance with licensing restrictions. Hardware specs and pricing sourced from official model cards and AWS pricing pages as of April 24, 2026. Pricing may change, always verify on vendor websites.