Saltar para o conteúdo principal
Local Engine Ready

DeepSeek R1 Distill 32B

10 consumer GPUs can run DeepSeek R1 Distill 32B at Q4 natively. Precise VRAM thresholds and benchmarks below.

10 Compatible GPUs
19 with offloading
32B params
128K context
Top pick
RTX 5090 · 32 GB VRAM runs Q4 natively

Prices and availability may change · affiliate link

Javier Morales
Javier Morales AI hardware specialist — 8 years of experience
GitHub: github.com/javier-morales-ia

llama.cpp 0.2.x · CUDA 12 · ROCm 6 · updated monthly · methodology →

Execution Context

ARCHITECTURE TRANSFORMER
CONTEXT 128K TOKENS
QUANTIZATION 4-BIT GGUF
PROVIDER DeepSeek
LICENSE MIT
VRAM REQUIREMENT
19.2 GB
4GB 8GB 12GB 16GB 24GB+
Hardware Decision

This model requires aHigh-end GPU (24 GB VRAM)

Minimum

RX 7900 XT

Runs at Q4 — functional, some wait

20 GB VRAM
View compatible setup
Balanced

M4 Max 48GB

Best value for daily use

48 GB VRAM
View compatible setup
Optimal

RTX 5090

Full quality, fastest inference

32 GB VRAM
View compatible setup

Compatible GPUs for DeepSeek R1 Distill 32B

Best picks by compatibility, VRAM headroom, and value — prices and availability may change.

RTX 5090
32 GB VRAM · Q4 native Amazon

RTX 5090

0.0 (0 avaliações)

Prós

  • Runs DeepSeek R1 Distill 32B at Q4 natively
  • 32 GB VRAM — adequate headroom
RTX 4090
24 GB VRAM · Q4 native Amazon

RTX 4090

4.8 (2,100 avaliações)

Prós

  • Runs DeepSeek R1 Distill 32B at Q4 natively
  • 24 GB VRAM — adequate headroom
M4 Ultra
128 GB VRAM · Q4 native Amazon

M4 Ultra

0.0 (0 avaliações)

Prós

  • Runs DeepSeek R1 Distill 32B at Q4 natively
  • 128 GB VRAM — adequate headroom

Alguns links são links de afiliado da Amazon. Podemos receber uma comissão sem custo adicional para si. O cookie da Amazon pode durar até 24 horas após o clique.

*Prices and availability may change. Some links are affiliate links.

System Requirements

GPU VRAM 19.2 GB High-end GPU
System RAM 29 GB 32 GB recommended
Storage 16 GB Q4 · SSD recommended
CPU Any modern CPU GPU required

VRAM by Quantization

Quantization VRAM needed Disk space Quality
FP16 (max quality) 76.8 GB 64 GB Maximum
Q8 (high quality) 38.4 GB 32 GB Near-lossless
Q4 (recommended) Best balance 19.2 GB 16 GB Recommended
Q2 (minimum) 9.6 GB 8 GB Quality loss

Model Details

Developer DeepSeek
Parameters 32B
Context window 128,000 tokens
License MIT
Use cases reasoning, chat, coding
Released 2025-01

Install with Ollama

ollama run deepseek-r1:32b

Hugging Face

deepseek-ai/DeepSeek-R1-Distill-Qwen-32B
View on HF →
Technical Requirements

Can your GPU run DeepSeek R1 Distill 32B?

DeepSeek R1 Distill 32B requires <strong class="text-primary-container">19.2 GB VRAM</strong> at Q4. 10 consumer GPUs meet this threshold. Below 8 GB or 17.2 GB you'll hit significant offload latency.

9.6GB Critical min
19.2GB Optimal Q4
38.4GB High Quality Q8
76.8GB Max FP16

Hardware Performance Matrix

10 Q4 native · 19 offload

GPU Unit VRAM Compatibility Est. Speed Action
RTX 5090 32GB Optimal Calculate →
RTX 4090 24GB Optimal Calculate →
M4 Ultra 128GB Optimal 26 tok/s Calculate →
M3 Ultra 192GB Optimal 20 tok/s Calculate →
RTX 3090 24GB Optimal Calculate →
M4 Max 48GB 48GB Optimal 13 tok/s Calculate →
RX 7900 XTX 24GB Optimal Calculate →
M4 Max 36GB 36GB Optimal Calculate →
RX 7900 XT 20GB Optimal Calculate →
M4 Pro 24GB Optimal Calculate →
RTX 5080 16GB Offload Calculate →
RTX 4080 Super 16GB Offload Calculate →
RTX 5070 Ti 16GB Offload Calculate →
RTX 4070 Ti Super 16GB Offload Calculate →
RTX 3080 Ti 12GB Offload Calculate →
RTX 5070 12GB Offload Calculate →
RTX 3080 10GB Offload Calculate →
RX 7800 XT 16GB Offload Calculate →
RX 6800 XT 16GB Offload Calculate →
RTX 4070 12GB Offload Calculate →
RTX 4060 Ti 16GB 16GB Offload Calculate →
RX 7700 XT 12GB Offload Calculate →
RX 6700 XT 12GB Offload Calculate →
M3 Pro 18GB Offload Calculate →
RTX 2080 Ti 11GB Offload Calculate →
RTX 3060 12GB Offload Calculate →
M2 Pro 16GB Offload Calculate →
Arc A770 16GB 16GB Offload Calculate →
M1 Pro 16GB Offload Calculate →

Recommended GPUs for DeepSeek R1 Distill 32B

Benchmarks reais
Sem reviews pagas
Escolha editorial
Baseado em dados

Best picks by compatibility, VRAM headroom, and value — prices and availability may change.

Alguns links são links de afiliado da Amazon. Podemos receber uma comissão sem custo adicional para si. O cookie da Amazon pode durar até 24 horas após o clique.

DeepSeek R1 Distill 32B — Compatibility guide

DeepSeek R1 Distill 32B requires a high-end GPU like the RTX 4090 or a Mac with M2 Ultra or better. The Q4 version needs 19.2 GB VRAM. Check the VRAM calculator for your options.

Compare GPUs for DeepSeek R1 Distill 32B

Which GPU is worth it? Real specs and benchmarks side by side.

Compatible Hardware

GPUs that run DeepSeek R1 Distill 32B at Q4 — sorted by AI performance score.

Benchmarks reais
Sem reviews pagas
Baseado em dados
RTX 5090

NVIDIA · 32 GB VRAM

Q4 OK
> $1000
RTX 4090

NVIDIA · 24 GB VRAM

Q4 OK
> $1000
M4 Ultra

Apple · 128 GB VRAM

Q4 OK
26 tok/s > $1000
M3 Ultra

Apple · 192 GB VRAM

Q4 OK
20 tok/s > $1000
RTX 3090

NVIDIA · 24 GB VRAM

Q4 OK
$600–1000
M4 Max 48GB

Apple · 48 GB VRAM

Q4 OK
13 tok/s > $1000

Alguns links são links de afiliado da Amazon. Podemos receber uma comissão sem custo adicional para si. O cookie da Amazon pode durar até 24 horas após o clique.

More Practical Alternatives

Similar models in the chat category with comparable VRAM footprints.

Compare This Model

See how DeepSeek R1 Distill 32B stacks up in head-to-head comparisons.

Not sure which GPU you need for DeepSeek R1 Distill 32B?

The VRAM Calculator tells you exactly which quantization your hardware can handle.

RTX 5090

Check availability

Preços mudam diariamente