Local LLM model page

DeepSeek R1 0528 Distill (8B)

Updated R1 reasoning distilled to Qwen3-8B. Improved chain-of-thought with fewer hallucinations vs original R1 distills. MIT licensed.

Find the best model for my hardwareBrowse all 183 LLMs
Parameters
8B
Minimum RAM
8 GB
Model size
5 GB
Quantization
Q4_K_M

Can DeepSeek R1 0528 Distill (8B) run locally?

DeepSeek R1 0528 Distill (8B) is best suited for entry-level laptops and desktops. LocalClaw recommends Q4_K_M as the default quantization, with at least 8 GB RAM.

Search term for LM Studio or compatible runtimes: deepseek-r1-0528-qwen3-8b

Hugging Face repository: deepseek-ai/DeepSeek-R1-0528-Qwen3-8B-GGUF

reasoningstandard

Strengths

  • Updated R1 reasoning distilled to Qwen3-8B. Improved chain-of-thought with fewer hallucinations vs original R1 distills. MIT licensed.

Limitations

  • Performance depends heavily on quantization, RAM bandwidth and runtime support.

Best use cases

  • reasoning
  • standard

Benchmarks

Speed: 8/10

Quality: 7/10

Coding: 7/10

Reasoning: 9/10

Technical details

Developer: deepseek

License: See model repository

Context window: Unknown tokens

Architecture: See model card

Released: 2025-05