BestLLMfor EN Your hardware. Your LLM. Your call.
APIOpen data Find my LLM
Model fiche

DeepSeek V3 671B

By DeepSeek · China

Updated 2026-07-13

chat general moe
Parameters
671B
License
DeepSeek License
Context
125k
VRAM (Q4)
400 GB
Released
December 2024

Overview

DeepSeek's frontier-open MoE — 671B total, 37B active — with multi-head latent attention and an auxiliary-loss-free balancing scheme. The V3.1-Terminus update relicenses under MIT.

When to pick this model

  • You're running server-class inference and want frontier-open performance
  • You need a non-reasoning frontier model for general chat and code at scale
  • You want the MLA architecture's reduced KV-cache footprint
  • You can move to V3.1-Terminus for MIT licensing

VRAM requirements by quantization

VRAM REQUIRED (GB)128256512Q4_K_M400 GBQ5_K_M480 GBQ8_0720 GBFP161342 GB
QuantizationVRAM required
Q4_K_M (recommended)400 GB
Q5_K_M480 GB
Q8_0720 GB
FP16 (no quantization)1342 GB

VRAM figures include model weights plus a typical 8k KV cache and ~600 MB runtime overhead (Ollama / llama.cpp baseline). Add headroom for higher context lengths.

In practice, DeepSeek V3 671B is server-class even at Q4_K_M (400 GB). Stepping up to Q8_0 nearly doubles the footprint to 720 GB, and unquantized FP16 weights take 1342 GB — plan your GPU around the Q4 or Q5 figure unless you specifically need the higher fidelity.

Without a GPU, DeepSeek V3 671B needs roughly 512 GB of system RAM to run on CPU via llama.cpp or Ollama — workable for background jobs, but far slower than GPU inference. Throughput estimates from our compatibility engine: around 1 tokens/sec on entry-level GPUs, on the order of 5 tokens/sec on a mid-range card, and up to 15 tokens/sec on high-end hardware — assuming the chosen quantization fully fits in VRAM.

What hardware do you need

The table below matches DeepSeek V3 671B to common GPU memory tiers, using the highest-fidelity quantization that fully fits each card class. Spilling layers to system RAM works but costs most of the speed, so size your card to the quantization you actually want to run.

GPU memoryExample cardsBest fit for DeepSeek V3 671B
8 GBRTX 5070 Laptop, RTX 5060, RTX 5060 Ti 8GBDoes not fit — needs 400 GB at Q4_K_M
12 GBRTX 5070, RTX 5070 Ti Laptop, RTX 4080 LaptopDoes not fit — needs 400 GB at Q4_K_M
16 GBRTX 5080, RTX 4080 Super, Radeon RX 9070 XTDoes not fit — needs 400 GB at Q4_K_M
24 GBRTX 4090, Radeon RX 7900 XTX, RTX 5090 LaptopDoes not fit — needs 400 GB at Q4_K_M
32 GBRTX 5090Does not fit — needs 400 GB at Q4_K_M

Which GPU should you buy to run DeepSeek V3 671B?

To run DeepSeek V3 671B locally at Q4, you need ~400 GB of VRAM. The best value for this is a Apple Mac Studio (64+ GB unified memory).

Check Apple Mac Studio price on Amazon →

As an Amazon Associate, BestLLMfor earns from qualifying purchases, at no extra cost to you. It does not influence our independent rankings.

Strengths

  • Frontier-open performance in chat, code, and general tasks
  • MLA cuts KV memory significantly vs standard attention
  • V3.1-Terminus available under MIT
  • Pretrained on 14.8T tokens

Limitations

  • Original V3 uses the restrictive DeepSeek License
  • 400GB+ in Q4 — server-class hardware only
  • Overkill for most workloads under 10B requests/month

Typical workloads

In our catalog grid, DeepSeek V3 671B is filed under Frontier Chat, Code, Reasoning — the use cases where its size/quality trade-off makes the most sense. Its tags translate to concrete workloads: everyday chat, drafting and summarization.

The 125k-token context window covers long chats and mid-sized documents, though very large retrieval workloads will need chunking. It ships under the DeepSeek License license — commercial use is generally possible but read the specific terms before embedding it in a product.

Architecture & training

Architecture: MoE 256 experts, 8 active · MLA · auxiliary-loss-free · FP8 training

Training: 14.8T tokens pre-training. V3.1-Terminus (Sep 2025) re-licensed MIT.

Verdict

Frontier-open performance for teams with serious inference infrastructure — go straight to V3.1-Terminus for the MIT license.

Quick start

ollama run deepseek-v3:671b

Or use the open-source MCP server to query this model from Claude Desktop, Cursor, or any MCP-compatible client.

Similar models worth comparing

Frequently asked questions

How much VRAM does DeepSeek V3 671B need?

At the recommended Q4_K_M quantization, DeepSeek V3 671B needs about 400 GB of VRAM. Q8_0 takes 720 GB, and unquantized FP16 weights take 1342 GB.

Can DeepSeek V3 671B run without a GPU?

Yes — with roughly 512 GB of system RAM it runs CPU-only through llama.cpp or Ollama. Expect a fraction of GPU speed, which is fine for background or batch jobs but slow for interactive chat.

What context window does DeepSeek V3 671B support?

DeepSeek V3 671B supports a 125k-token context window (128,000 tokens).

Can I use DeepSeek V3 671B commercially?

DeepSeek V3 671B ships under the DeepSeek License license. Commercial use is generally permitted subject to its terms — review the license text before shipping a product.

How fast is DeepSeek V3 671B on consumer hardware?

Our compatibility engine estimates on the order of 5 tokens/sec on a mid-range GPU and up to 15 tokens/sec on high-end cards, assuming the quantization fully fits in VRAM.

Which quantization of DeepSeek V3 671B should I download first?

Start with Q4_K_M (400 GB) — the standard size/quality sweet spot. Step up to Q5_K_M or Q8_0 only if you have VRAM headroom. It does not fit a single 24 GB consumer card — plan for multi-GPU or server hardware.

Tools

Is DeepSeek V3 671B the right pick for you?

Compute self-hosted ROI → Back to catalog