Local LLM model page

DeepSeek R1 0528 (671B MoE)

Updated flagship DeepSeek R1 with improved reasoning chains and fewer hallucinations. Major upgrade to chain-of-thought quality. MIT licensed. Server-grade only.

Find the best model for my hardware Browse all 183 LLMs

Parameters

671B (37B active)

Minimum RAM

512 GB

Model size

360 GB

Quantization

Q4_K_M

Can DeepSeek R1 0528 (671B MoE) run locally?

DeepSeek R1 0528 (671B MoE) is best suited for server-grade or multi-GPU systems. LocalClaw recommends Q4_K_M as the default quantization, with at least 512 GB RAM.

Search term for LM Studio or compatible runtimes: deepseek-r1-0528

Hugging Face repository: deepseek-ai/DeepSeek-R1-0528-GGUF

reasoningcodequality

Strengths

Significantly improved reasoning chains vs original R1
Fewer hallucinations and better self-correction
MIT license — fully open
128K context
State-of-the-art on math and coding benchmarks

Limitations

Requires 512GB+ RAM (server-grade only)
Slower than non-reasoning models
Still verbose in reasoning chains

Best use cases

Server-grade reasoning deployment
Mathematical research
Complex coding tasks
Scientific analysis
Enterprise on-premise AI

Benchmarks

Speed: 1/10

Quality: 10/10

Coding: 10/10

Reasoning: 10/10

Technical details

Developer: DeepSeek AI

License: MIT

Context window: 131,072 tokens

Architecture: Mixture of Experts (MoE) — 671B total, 37B active per token. Updated from original R1.

Released: 2025-05