Can the RTX 4090 24GB run DeepSeek-R1 Distill Qwen 32B?

AIPCFit compares the model's recorded GGUF variants against the24GB of dedicated VRAM on the RTX 4090 24GB. The result is a deterministic memory-planning check, not a speed benchmark.

GPU: RTX 4090 24GB
Dedicated VRAM: 24 GB
Model: DeepSeek-R1 Distill Qwen 32B
Best recorded fit: Fits

Quick answer

DeepSeek-R1 Distill Qwen 32B has a memory-fit path on the RTX 4090 24GB

At least one recorded variant reaches AIPCFit's good-fit or fits threshold using this GPU's dedicated VRAM. Exact speed, context capacity, and runtime behavior are not predicted here.

Variant-by-variant fit

DeepSeek-R1 Distill Qwen 32B variants on RTX 4090 24GB

DeepSeek-R1 Distill Qwen 32B · Q4_K_M

GGUF · Q4_K_M

Fits

Model-size signal: 20 GB
Minimum load: 23 GB
Planning memory: 27 GB
GPU VRAM: 24 GB

24 GB dedicated VRAM meets the 23 GB minimum-load planning level, but not the 27 GB recommended headroom.

Expect less room for long context or concurrent GPU work.

What this compatibility result does not claim

No speed estimate

AIPCFit does not invent tokens-per-second numbers.

No fake system RAM

This page does not assume how much RAM your full PC has, so partial offload is not ranked.

No universal context guarantee

Longer context and runtime settings can increase real memory pressure.

Explore related local AI guides

RTX 4090 24GB local AI guide DeepSeek-R1 Distill Qwen 32B model guide 24GB VRAM models Check my full PC