LocalClaw/LLM/DeepSeek V3.2 (37B/671B MoE)
Open-weight MoE

DeepSeek V3.2 (37B/671B MoE)

DeepSeek's massive MoE flagship. 37B active out of 671B total. Exceptional coding, reasoning and general capabilities. Ranks #6 on global usage leaderboards with 29B monthly tokens. MIT licensed.

64 GB workstation 48 GB RAM Q4_K_M Enterprise AI
Run with LocalClaw Compare all models
Parameters
37B (671B MoE)
Minimum RAM
48 GB
Model size
40 GB
Quantization
Q4_K_M

Can DeepSeek V3.2 (37B/671B MoE) run locally?

DeepSeek V3.2 (37B/671B MoE) is best for 64 GB workstations and larger Apple Silicon or NVIDIA setups.

Search for deepseek-v3.2 in LM Studio or another GGUF-compatible runtime.

deepseek-ai/DeepSeek-V3.2-GGUF
chatcodereasoningpowerqualitygeneral

Install path

01
Check RAM fitMinimum 48 GB RAM. Start with the Q4_K_M quant.
02
Load the modelSearch deepseek-v3.2 in LM Studio.
03
Control locallyUse LocalClaw to manage models, agents, chat, channels and scheduled OpenClaw work.

Strengths

  • Latest DeepSeek MoE flagship
  • Ranks #6 globally with 29B monthly tokens
  • MIT license
  • Exceptional coding and reasoning

Limitations

  • Requires 48GB+ RAM
  • Server-grade recommended
  • Complex setup

Best use cases

  • Enterprise AI
  • Research
  • Complex coding
  • Reasoning at scale

Capability profile

speed
3
quality
10
coding
10
reasoning
10

Technical notes

Developer
DeepSeek AI
License
MIT
Context window
131,072 tokens
Architecture
Mixture of Experts (MoE) — 671B total, ~37B active

This model fits these next steps

Hardware fit is based on LocalClaw's RAM tier, model size and quantization metadata. Always leave memory headroom for your OS and runtime.

Workstation fitMac Studio M4 Max 64GBCUDA workstation classNVIDIA GB10 / DGX SparkLarge local models64GB RAM guide

Similar models to compare

DeepSeek V3.1 (671B MoE) 671B (37B active, MoE)Trinity Large Preview (70B MoE) 70B (MoE, ~400B total)Llama 3.3 (70B) 70B

Where to go next