Skip to content

Nemotron 3.5 Lightning 30B A3B on 4× RTX 3090: VRAM, speed and fit

Nemotron 3.5 Lightning 30B A3B at 8-bit runs on the 4× RTX 3090 with 256K of context at about 124 tokens a second.

Text generation · Chat · Ollama / LM Studio

Runs comfortably · on 4× RTX 3090 · 8-bit (Q8_0) · Ollama / LM Studio · Chat

GPU memory
35.4 GB
of 96.0 GB
Context
256K
auto
Speed
124 tok/s
95 when full
First reply
0.2 s
2K prompt

Where the memory goes

Model
31.2 GB
Context
1.5 GB
Overhead
2.6 GB
OS
0.0 GB
Free
60.6 GB
Memory
35.4 GB of 96.0 GB
Context
256K tokens · auto
Speed
124 tok/s · 95 when full
First reply
0.2 s for a 2K prompt
Running cost
$20/mo at home · $61/mo on a cloud 2× RTX A4500

Validation: Validated

What Nemotron 3.5 Lightning 30B A3B on 4× RTX 3090 was checked against
CheckTargetResultStatus
Fits in GPU memory96.0 GB usable35.4 GB neededPass
Headroom5% free60.6 GB free (63%)Pass
Context for chat16K or more256KPass
Writing speed15 tok/s or more124 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
Nemotron 3.5 Lightning 30B A3B
Parameters
31.6B, 3B active
Precision
8-bit (Q8_0)
Context
256K, auto
Chats at once
1
Use
Chat
Runs in
Ollama / LM Studio
Hardware
4× RTX 3090
GPU can use
96.0 GB of 96.0 GB

Running cost

At home
$20/mo
920 W at the wall
Renting instead
$61/mo
2× RTX A4500 at $0.50/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

Ollama
ollama run nemotron-3.5-lightning:30b-a3b
llama.cpp
llama-server -hf unsloth/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-GGUF
vLLM
vllm serve nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16
MLX (Mac)
mlx_lm.chat --model mlx-community/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-4bit

Nemotron 3.5 Lightning 30B A3B on similar machines

Other models that run on 4× RTX 3090

Questions

Can Nemotron 3.5 Lightning 30B A3B run on 4× RTX 3090?

Nemotron 3.5 Lightning 30B A3B at 8-bit runs on the 4× RTX 3090 with 256K of context at about 124 tokens a second.

Report VR-18S7YID, calculated Nov 22, 2026 from published specs, not benchmarked.