Skip to content

Qwen3 Coder 30B A3B Instruct on RTX 5090: VRAM, speed and fit

Qwen3 Coder 30B A3B Instruct at 6-bit runs on the RTX 5090 with 64K of context at about 207 tokens a second.

Text generation · Chat · Ollama / LM Studio

Runs comfortably · on RTX 5090 · 6-bit (Q6_K) · Ollama / LM Studio · Chat

GPU memory
30.1 GB
of 32.0 GB
Context
64K
auto
Speed
207 tok/s
100 when full
First reply
0.2 s
2K prompt

Where the memory goes

Model
23.3 GB
Context
6.0 GB
Overhead
822 MB
OS
0.0 GB
Free
1.9 GB
Memory
30.1 GB of 32.0 GB
Context
64K tokens · auto
Speed
207 tok/s · 100 when full
First reply
0.2 s for a 2K prompt
Running cost
$9.30/mo at home · $58/mo on a cloud 2× RTX 2000 Ada

Validation: Validated

What Qwen3 Coder 30B A3B Instruct on RTX 5090 was checked against
CheckTargetResultStatus
Fits in GPU memory32.0 GB usable30.1 GB neededPass
Headroom5% free1.9 GB free (6%)Pass
Context for chat16K or more64KPass
Writing speed15 tok/s or more207 tok/sPass
First replyunder 3 s, 2K prompt0.2 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
Qwen3 Coder 30B A3B Instruct
Parameters
30.5B, 3B active
Precision
6-bit (Q6_K)
Context
64K, auto
Chats at once
1
Use
Chat
Runs in
Ollama / LM Studio
Hardware
RTX 5090
GPU can use
32.0 GB of 32.0 GB

Running cost

At home
$9.30/mo
425 W at the wall
Renting instead
$58/mo
2× RTX 2000 Ada at $0.48/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/Qwen3-Coder-30B-A3B-Instruct-GGUF
vLLM
vllm serve Qwen/Qwen3-Coder-30B-A3B-Instruct
MLX (Mac)
mlx_lm.chat --model mlx-community/Qwen3-Coder-30B-A3B-Instruct-4bit

Qwen3 Coder 30B A3B Instruct on similar machines

All machines: Qwen3 Coder 30B A3B Instruct VRAM requirements. Everything that runs here: what can the RTX 5090 run?

Other models that run on RTX 5090

Questions

Can Qwen3 Coder 30B A3B Instruct run on RTX 5090?

Qwen3 Coder 30B A3B Instruct at 6-bit runs on the RTX 5090 with 64K of context at about 207 tokens a second.

Report VR-1S5KKX6, calculated Nov 22, 2026 from published specs, not benchmarked.