Skip to main content

Can the RTX 3090 Run DeepSeek-R1-Distill-Qwen 32B?

Runs

Yes. DeepSeek-R1-Distill-Qwen 32B at Q4_K_M is a 19.9 GB download (Hugging Face file listing for bartowski/DeepSeek-R1-Distill-Qwen-32B-GGUF), and the RTX 3090 has 24 GB of VRAM, leaving about 4.1 GB for the KV cache and runtime. No published speed measurement for this pair passes SpecPicks' sanity checks yet, so no tokens-per-second figure is quoted.

Model file19.9 GBQ4_K_M
VRAM24 GBRTX 3090
Headroom4.1 GBafter weights
Median speed0 cited runs
Bandwidth ceiling~47 tok/s936 GB/s ÷ 19.9 GB

Published runs for DeepSeek-R1-Distill-Qwen 32B on the RTX 3090

No published run for this pair has passed the checks yet.

More about this pair

How much VRAM does DeepSeek-R1-Distill-Qwen 32B need?

The Q4_K_M file is 19.9 GB. Add roughly 1.5 GB for the runtime and an ~8K-token context, so about 21.4 GB of VRAM holds it comfortably. Longer contexts grow the KV cache and need more.

What is the fastest DeepSeek-R1-Distill-Qwen 32B can generate on the RTX 3090?

Generation reads every weight once per token, so the RTX 3090's 936 GB/s of memory bandwidth divided by the 19.9 GB file sets a ceiling near 47 tokens per second. Real runs land below it; SpecPicks rejects any published figure above it.

Check another pair

See the full matrix → · All RTX 3090 benchmarks →

DeepSeek-R1-Distill-Qwen 32B on other GPUs

Other models on the RTX 3090

How the checks work

The fit is the Q4_K_M file size against the card's VRAM, with 1.5 GB kept for the runtime and an ~8K context. A published run counts only if the pair fits, the run is Q4-class, its source does not call it an estimate, it is under the bandwidth ceiling above, and it is not one figure pasted across many cards. The whole matrix is downloadable as a CSV under CC BY 4.0.

As an Amazon Associate, SpecPicks earns from qualifying purchases.

This page is editorial synthesis based on publicly available information. No independent first-party benchmarking is reported.