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

DeepSeek V3.2

By DeepSeek · China

Updated 2026-07-13

chat general moe
Parameters
685B
License
MIT
Context
125k
VRAM (Q4)
410 GB
Released
December 2025

Overview

DeepSeek's 685B MoE featuring DeepSeek Sparse Attention for lower memory use. Holds an IMO gold-medal score and ranks #2 by volume on OpenRouter.

When to pick this model

  • Frontier-class generalist tasks on a multi-GPU server
  • Competition-level math and reasoning
  • Replacing closed APIs with MIT-licensed weights
  • High-volume production inference
  • Long-context enterprise workloads

VRAM requirements by quantization

VRAM REQUIRED (GB)128256512Q4_K_M410 GBQ5_K_M490 GBQ8_0735 GBFP161370 GB
QuantizationVRAM required
Q4_K_M (recommended)410 GB
Q5_K_M490 GB
Q8_0735 GB
FP16 (no quantization)1370 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 V3.2 is server-class even at Q4_K_M (410 GB). Stepping up to Q8_0 nearly doubles the footprint to 735 GB, and unquantized FP16 weights take 1370 GB — plan your GPU around the Q4 or Q5 figure unless you specifically need the higher fidelity.

Without a GPU, DeepSeek V3.2 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 V3.2 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 V3.2
8 GBRTX 5070 Laptop, RTX 5060, RTX 5060 Ti 8GBDoes not fit — needs 410 GB at Q4_K_M
12 GBRTX 5070, RTX 5070 Ti Laptop, RTX 4080 LaptopDoes not fit — needs 410 GB at Q4_K_M
16 GBRTX 5080, RTX 4080 Super, Radeon RX 9070 XTDoes not fit — needs 410 GB at Q4_K_M
24 GBRTX 4090, Radeon RX 7900 XTX, RTX 5090 LaptopDoes not fit — needs 410 GB at Q4_K_M
32 GBRTX 5090Does not fit — needs 410 GB at Q4_K_M

Which GPU should you buy to run DeepSeek V3.2?

To run DeepSeek V3.2 locally at Q4, you need ~410 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

  • IMO gold-medal reasoning quality
  • DeepSeek Sparse Attention reduces memory pressure
  • MIT license
  • #2 by usage volume on OpenRouter

Limitations

  • 410GB+ in Q4 needs a serious multi-GPU server
  • Sparse attention adds inference engine complexity
  • Operational overhead is significant

Typical workloads

In our catalog grid, DeepSeek V3.2 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. The MIT license is permissive, so shipping it inside a commercial product raises no special legal questions.

Architecture & training

Architecture: MoE 685B/37B active · DeepSeek Sparse Attention · MIT

Training: V3 successor with DSA for reduced memory.

Verdict

A frontier-grade MIT-licensed MoE if you can run a multi-GPU cluster.

Quick start

# HuggingFace : deepseek-ai/DeepSeek-V3.2 (alternative locale : 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 V3.2 need?

At the recommended Q4_K_M quantization, DeepSeek V3.2 needs about 410 GB of VRAM. Q8_0 takes 735 GB, and unquantized FP16 weights take 1370 GB.

Can DeepSeek V3.2 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 V3.2 support?

DeepSeek V3.2 supports a 125k-token context window (128,000 tokens).

Can I use DeepSeek V3.2 commercially?

Yes. DeepSeek V3.2 is released under MIT, a permissive open-source license that allows commercial use, modification and redistribution.

How fast is DeepSeek V3.2 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 V3.2 should I download first?

Start with Q4_K_M (410 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 V3.2 the right pick for you?

Compute self-hosted ROI → Back to catalog