Skip to content

Granite 3.3 8B Instruct on 2× RTX 3090: VRAM, speed and fit

Granite 3.3 8B Instruct at 8-bit runs on the 2× RTX 3090 with 128K of context at about 69 tokens a second.

Text generation · Chat · Ollama / LM Studio

Runs comfortably · on 2× RTX 3090 · 8-bit (Q8_0) · Ollama / LM Studio · Chat

GPU memory
29.3 GB
of 48.0 GB
Context
128K
auto
Speed
69 tok/s
21 when full
First reply
0.3 s
2K prompt

Where the memory goes

Model
8.1 GB
Context
20.0 GB
Overhead
1.2 GB
OS
0.0 GB
Free
18.7 GB
Memory
29.3 GB of 48.0 GB
Context
128K tokens · auto
Speed
69 tok/s · 21 when full
First reply
0.3 s for a 2K prompt
Running cost
$11/mo at home · $58/mo on a cloud 2× RTX 2000 Ada

Validation: Validated

What Granite 3.3 8B Instruct on 2× RTX 3090 was checked against
CheckTargetResultStatus
Fits in GPU memory48.0 GB usable29.3 GB neededPass
Headroom5% free18.7 GB free (39%)Pass
Context for chat16K or more128KPass
Writing speed15 tok/s or more69 tok/sPass
First replyunder 3 s, 2K prompt0.3 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
Granite 3.3 8B Instruct
Parameters
8.2B
Precision
8-bit (Q8_0)
Context
128K, auto
Chats at once
1
Use
Chat
Runs in
Ollama / LM Studio
Hardware
2× RTX 3090
GPU can use
48.0 GB of 48.0 GB

Running cost

At home
$11/mo
500 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 22, 2026.

How to run it

llama.cpp
llama-server -hf ibm-granite/granite-3.3-8b-instruct-GGUF
vLLM
vllm serve ibm-granite/granite-3.3-8b-instruct
MLX (Mac)
mlx_lm.chat --model mlx-community/granite-3.3-8b-instruct-4bit

Granite 3.3 8B Instruct on similar machines

All machines: Granite 3.3 8B Instruct VRAM requirements. Everything that runs here: what can the 2× RTX 3090 run?

Other models that run on 2× RTX 3090

Questions

Can Granite 3.3 8B Instruct run on 2× RTX 3090?

Granite 3.3 8B Instruct at 8-bit runs on the 2× RTX 3090 with 128K of context at about 69 tokens a second.

Report VR-1S2ICQV, calculated Nov 22, 2026 from published specs, not benchmarked.