Skip to content

Qwen3 Next 80B A3B Instruct on 2× RTX 5090: VRAM, speed and fit

Qwen3 Next 80B A3B Instruct at 5-bit runs on the 2× RTX 5090 with 224K of context at about 215 tokens a second.

Text generation · Chat · Ollama / LM Studio

Runs comfortably · on 2× RTX 5090 · 5-bit (Q5_K_M) · Ollama / LM Studio · Chat

GPU memory
60.6 GB
of 64.0 GB
Context
224K
auto
Speed
215 tok/s
109 when full
First reply
0.1 s
2K prompt

Where the memory goes

Model
53.9 GB
Context
5.3 GB
Overhead
1.4 GB
OS
0.0 GB
Free
3.4 GB
Memory
60.6 GB of 64.0 GB
Context
224K tokens · auto
Speed
215 tok/s · 109 when full
First reply
0.1 s for a 2K prompt
Running cost
$17/mo at home · $117/mo on a cloud 4× RTX 2000 Ada

Validation: Validated

What Qwen3 Next 80B A3B Instruct on 2× RTX 5090 was checked against
CheckTargetResultStatus
Fits in GPU memory64.0 GB usable60.6 GB neededPass
Headroom5% free3.4 GB free (5%)Pass
Context for chat16K or more224KPass
Writing speed15 tok/s or more215 tok/sPass
First replyunder 3 s, 2K prompt0.1 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 Next 80B A3B Instruct
Parameters
81.3B, 3B active
Precision
5-bit (Q5_K_M)
Context
224K, auto
Chats at once
1
Use
Chat
Runs in
Ollama / LM Studio
Hardware
2× RTX 5090
GPU can use
64.0 GB of 64.0 GB

Running cost

At home
$17/mo
770 W at the wall
Renting instead
$117/mo
4× RTX 2000 Ada at $0.96/h

4 h a day, power at $0.18 per kWh, cloud at RunPod on-demand prices as of Nov 22, 2026.

How to run it

llama.cpp
llama-server -hf unsloth/Qwen3-Next-80B-A3B-Instruct-GGUF
vLLM
vllm serve Qwen/Qwen3-Next-80B-A3B-Instruct
MLX (Mac)
mlx_lm.chat --model mlx-community/Qwen3-Next-80B-A3B-Instruct-4bit

Qwen3 Next 80B A3B Instruct on similar machines

All machines: Qwen3 Next 80B A3B Instruct VRAM requirements. Everything that runs here: what can the 2× RTX 5090 run?

Other models that run on 2× RTX 5090

Questions

Can Qwen3 Next 80B A3B Instruct run on 2× RTX 5090?

Qwen3 Next 80B A3B Instruct at 5-bit runs on the 2× RTX 5090 with 224K of context at about 215 tokens a second.

Report VR-01C9YLH, calculated Nov 22, 2026 from published specs, not benchmarked.