Skip to content

DeepSeek R1 0528 Qwen3 8B on RTX 3090: VRAM, speed and fit

DeepSeek R1 0528 Qwen3 8B at 8-bit runs on the RTX 3090 with 96K of context at about 75 tokens a second.

Text generation · Chat · Ollama / LM Studio

Runs comfortably · on RTX 3090 · 8-bit (Q8_0) · Ollama / LM Studio · Chat

GPU memory
22.5 GB
of 24.0 GB
Context
96K
auto
Speed
75 tok/s
28 when full
First reply
0.4 s
2K prompt

Where the memory goes

Model
8.1 GB
Context
13.5 GB
Overhead
886 MB
OS
0.0 GB
Free
1.5 GB
Memory
22.5 GB of 24.0 GB
Context
96K tokens · auto
Speed
75 tok/s · 28 when full
First reply
0.4 s for a 2K prompt
Running cost
$6.35/mo at home · $33/mo on a cloud RTX A5000

Validation: Validated

What DeepSeek R1 0528 Qwen3 8B on RTX 3090 was checked against
CheckTargetResultStatus
Fits in GPU memory24.0 GB usable22.5 GB neededPass
Headroom5% free1.5 GB free (6%)Pass
Context for chat16K or more96KPass
Writing speed15 tok/s or more75 tok/sPass
First replyunder 3 s, 2K prompt0.4 sPass

Targets: a reply you can read along with, a first reply the use case tolerates, and 5% of memory left free. Calculated from published specs, not benchmarked.

The setup

Model
DeepSeek R1 0528 Qwen3 8B
Parameters
8.2B
Precision
8-bit (Q8_0)
Context
96K, auto
Chats at once
1
Use
Chat
Runs in
Ollama / LM Studio
Hardware
RTX 3090
GPU can use
24.0 GB of 24.0 GB

Running cost

At home
$6.35/mo
290 W at the wall
Renting instead
$33/mo
RTX A5000 at $0.27/h

4 h a day, power at $0.18 per kWh, cloud at RunPod on-demand prices as of Nov 21, 2026.

How to run it

llama.cpp
llama-server -hf unsloth/DeepSeek-R1-0528-Qwen3-8B-GGUF
vLLM
vllm serve deepseek-ai/DeepSeek-R1-0528-Qwen3-8B
MLX (Mac)
mlx_lm.chat --model mlx-community/DeepSeek-R1-0528-Qwen3-8B-4bit

DeepSeek R1 0528 Qwen3 8B on similar machines

All machines: DeepSeek R1 0528 Qwen3 8B VRAM requirements. Everything that runs here: what can the RTX 3090 run?

Other models that run on RTX 3090

Questions

Can DeepSeek R1 0528 Qwen3 8B run on RTX 3090?

DeepSeek R1 0528 Qwen3 8B at 8-bit runs on the RTX 3090 with 96K of context at about 75 tokens a second.

Report VR-1XPMQ9X, calculated Nov 22, 2026 from published specs, not benchmarked.