DeepSeek R1 Distill 32B

Overview

The 32B DeepSeek R1 distill — the best accessible open-weight reasoner we've tested. Explicit chain-of-thought, MIT-licensed, runs on a single 24GB GPU.

When to pick this model

• Math, logic, and proof-style problems
• Code debugging where explicit reasoning helps
• Research workflows needing visible chain-of-thought
• Self-hosted alternatives to o1-mini-class APIs
• Commercial use under MIT license

VRAM requirements by quantization

Quantization	VRAM required
Q4_K_M (recommended)	19 GB
Q5_K_M	23 GB
Q8_0	35 GB
FP16 (no quantization)	64 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.

Published benchmark scores

Benchmark	Score
AIME 2024	72.6
MATH-500	94.3
GPQA	62.1

Scores published by the model author or aggregated from public leaderboards. Re-measured monthly by our editorial team.

Strengths

• Best open-weight reasoner that fits on one consumer GPU
• Excellent math and science performance
• Explicit step-by-step thinking
• MIT license
• 32k context

Limitations

• Heavy thinking-token output inflates latency and cost
• Slow time-to-first-useful-answer
• 32k context is shorter than most 2025 peers
• Overkill for simple chat

Architecture & training

Architecture: DeepSeek R1 distillation · reinforced chain-of-thought

Training: Distilled from R1 671B · RL on reasoning problems.

Quick start

ollama run deepseek-r1:32b

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